# Events Calendar

﻿

#### Filter March Events by Event Type:

SUNMONTUEWEDTHUFRISAT

## Conferences, Lectures, & SeminarsEvents for March

• ### CS Colloquium: Hengshuang Zhao (University of Oxford) - Advancing Visual Intelligence via Neural System Design

Mon, Mar 01, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Hengshuang Zhao, University of Oxford

Talk Title: Advancing Visual Intelligence via Neural System Design

Series: CS Colloquium

Abstract: Building intelligent visual systems is essential for the next generation of artificial intelligence systems. It is a fundamental tool for many disciplines and beneficial to various potential applications such as autonomous driving, robotics, surveillance, augmented reality, to name a few. An accurate and efficient intelligent visual system has a deep understanding of the scene, objects, and humans. It can automatically understand the surrounding scenes. In general, 2D images and 3D point clouds are the two most common data representations in our daily life. Designing powerful image understanding and point cloud processing systems are two pillars of visual intelligence, enabling the artificial intelligence systems to understand and interact with the current status of the environment automatically. In this talk, I will first present our efforts in designing modern neural systems for 2D image understanding, including high-accuracy and high-efficiency semantic parsing structures, and unified panoptic parsing architecture. Then, we go one step further to design neural systems for processing complex 3D scenes, including semantic-level and instance-level understanding. Further, we show our latest works for unified 2D-3D reasoning frameworks, which are fully based on self-attention mechanisms. In the end, the challenges, up-to-date progress, and promising future directions for building advanced intelligent visual systems will be discussed.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Dr. Hengshuang Zhao is a postdoctoral researcher at the University of Oxford. Before that, he obtained his Ph.D. degree from the Chinese University of Hong Kong. His general research interests cover the broad area of computer vision, machine learning and artificial intelligence, with special emphasis on building intelligent visual systems. He and his team won several champions in competitive international challenges like ImageNet Scene Parsing Challenge. He is recognized as outstanding/top reviewers in ICCV'19 and NeurIPS'19. He receives the rising star award at the world artificial intelligence conference 2020. Some of his research projects are supported by Microsoft, Adobe, Uber, Intel, and Apple. His works have been cited for about 5,000+ times, with 5,000+ GitHub credits and 80,000+ YouTube views.

Host: Ramakant Nevatia

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

• ### CS Colloquium: Leilani Gilpin (MIT CSAIL) - Anomaly Detection Through Explanations

Tue, Mar 02, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Leilani Gilpin, MIT CSAIL

Talk Title: Anomaly Detection Through Explanations

Series: CS Colloquium

Abstract: Under most conditions, complex systems are imperfect. When errors occur, as they inevitably will, systems need to be able to (1) localize the error and (2) take appropriate action to mitigate the repercussions of that error. In this talk, I present new methodologies for detecting and explaining errors in complex systems.
My novel contribution is a system-wide monitoring architecture, which is composed of introspective, overlapping committees of subsystems.
Each subsystem is encapsulated in a "reasonableness" monitor, an adaptable framework that supplements local decisions with commonsense data and reasonableness rules. This framework is dynamic and introspective: it allows each subsystem to defend its decisions in different contexts: to the committees it participates in and to itself. For reconciling system-wide errors, I developed a comprehensive architecture: "Anomaly Detection through Explanations (ADE)." The ADE architecture contributes an explanation synthesizer that produces an argument tree, which in turn can be traced and queried to determine the support of a decision, and to construct counterfactual explanations. I have applied this methodology to detect incorrect labels in semi-autonomous vehicle data, and to reconcile inconsistencies in simulated, anomalous driving scenarios.

My work has opened up the new area of explanatory anomaly detection, towards a vision in which: complex machines will be articulate by design; dynamic, internal explanations will be part of the design criteria, and system-level explanations will be able to be challenged in an adversarial proceeding.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Leilani H. Gilpin is a research scientist at Sony AI and a collaborating researcher at MIT CSAIL. Her research focuses on enabling opaque autonomous systems to explain themselves for robust decision-making, system debugging, and accountability. Her current work integrates explainability into reinforcement learning for game-playing agents.

She received her PhD in Electrical Engineering and Computer Science from MIT in 2020, and holds an M.S. in Computational and Mathematical Engineering from Stanford University, and a B.S. in Mathematics (with honors), B.S. in Computer Science (with highest honors), and a music minor from UC San Diego. Outside of research, Leilani enjoys swimming, cooking, and rowing.

Host: Yan Liu

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

• ### Astani Department of Civil and Environmental Engineering Seminar

Tue, Mar 02, 2021 @ 11:00 AM - 12:00 PM

Sonny Astani Department of Civil and Environmental Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Hadi Meidani, Assistant Professor, University of Illinois at Urbana-Champaign

Talk Title: Scientific Machine Learning for Efficient Computational Design of Engineering Systems

Abstract:
The focus of this talk is on using deep neural networks (DNNs) to approximate the response of engineering systems and facilitate their design and control. DNNs can be trained using supervised learning approaches which require large datasets of input-output samples. In engineering applications, these input-output samples are typically obtained from high-fidelity Finite Element or Finite Difference solvers. In applications where these samples are costly to obtain, supervised learning may be prohibitively slow. In this talk, I will present our recent contributions in this domain, which includes (1) using DNNs to accelerate robust topology optimization via a lower-dimensional representation and (2) developing a PDE-based simulation-free deep learning approach that directly exploit the physical laws in an efficient way.

Biography: Hadi Meidani is an Assistant Professor in the Department of Civil and Environmental Engineering at the University of Illinois at Urbana-Champaign. He earned his Ph.D. in Civil Engineering and his M.S. in Electrical Engineering from the University of Southern California in 2012. Prior to joining UIUC, he was a postdoctoral research associate at USC in (2012-2013) and in the Scientific Computing and Imaging Institute at the University of Utah (2013-2014). He is the recipient of the NSF CAREER Award to study fast computational models for infrastructure systems. His research interests are uncertainty quantification, scientific machine learning, and design under uncertainty.

Host: Dr. Roger Ghanem

Location: Zoom: https://usc.zoom.us/j/97228056404; Meeting ID: 972 2805 6404: Passcode: 864779

Audiences: Everyone Is Invited

Contact: Evangeline Reyes

• ### ISE 651 - Epstein Seminar

Tue, Mar 02, 2021 @ 03:30 PM - 04:50 PM

Daniel J. Epstein Department of Industrial and Systems Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Meisam Razaviyayn, Assistant Professor, Epstein Dept. of Industrial & Systems Engineering, USC

Talk Title: Does Your Training Data Violate My Privacy? A Near-Optimal Model Discrimination Method With Non-Disclosure

Host: Prof. Jong-Shi Pang

Location: Online/Zoom

Audiences: Everyone Is Invited

Contact: Grace Owh

• ### Mork Family Department Spring Virtual Seminars - Ilya Levental

Tue, Mar 02, 2021 @ 04:00 PM - 05:20 PM

Mork Family Department of Chemical Engineering and Materials Science

Conferences, Lectures, & Seminars

Speaker: Ilya Levental, University of Virginia

Talk Title: DESIGN PRINCIPLES OF LIVING MEMBRANES

Abstract: ZOOM MEETING INFO:
https://usc.zoom.us/j/98225952695?pwd=d0NMenhCNkliR1ZIR1lBamRpZHh1UT09
Meeting ID: 982 2595 2695 • Passcode: 322435

Audiences: Everyone Is Invited

Contact: Greta Harrison

• ### CS Colloquium: Zhuoran Yang (Princeton University) - Demystifying (Deep) Reinforcement Learning: The Pessimist, The Optimist, and Their Provable Efficiency

Wed, Mar 03, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Zhuoran Yang, Princeton University

Talk Title: Demystifying (Deep) Reinforcement Learning: The Pessimist, The Optimist, and Their Provable Efficiency

Series: CS Colloquium

Abstract: Coupled with powerful function approximators such as deep neural networks, reinforcement learning (RL) achieves tremendous empirical successes. However, its theoretical understandings lag behind. In particular, it remains unclear how to provably attain the optimal policy with a finite regret or sample complexity. In this talk, we will present the two sides of the same coin, which demonstrates an intriguing duality between pessimism and optimism.

- In the offline setting, we aim to learn the optimal policy based on a dataset collected a priori. Due to a lack of active interactions with the environment, we suffer from the insufficient coverage of the dataset. To maximally exploit the dataset, we propose a pessimistic least-squares value iteration algorithm, which achieves a minimax-optimal sample complexity.

- In the online setting, we aim to learn the optimal policy by actively interacting with an environment. To strike a balance between exploration and exploitation, we propose an optimistic least-squares value iteration algorithm, which achieves a \sqrt{T} regret in the presence of linear, kernel, and neural function approximators.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Zhuoran Yang is a final-year Ph.D. student in the Department of Operations Research and Financial Engineering at Princeton University, advised by Professor Jianqing Fan and Professor Han Liu. Before attending Princeton, He obtained a Bachelor of Mathematics degree from Tsinghua University. His research interests lie in the interface between machine learning, statistics, and optimization. The primary goal of his research is to design a new generation of machine learning algorithms for large-scale and multi-agent decision-making problems, with both statistical and computational guarantees. Besides, he is also interested in the application of learning-based decision-making algorithms to real-world problems that arise in robotics, personalized medicine, and computational social science.

Host: Haipeng Luo

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

• ### Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar

Wed, Mar 03, 2021 @ 02:00 PM - 03:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Gabor Orosz, Mechanical Engineering, University of Michigan

Talk Title: Safety Verification and Conflict Analysis for Connected Automated Vehicles

Series: Center for Cyber-Physical Systems and Internet of Things

Abstract: We demonstrate how wireless vehicle-to-everything (V2X) communication can be utilized to improve safety and prevent conflicts between road participants in mixed traffic scenarios where connected automated vehicles (CAVs) interact with connected human-driven vehicles (CHVs). The key idea is to find boundaries in state space that allow CAVs to make safe decisions far away from the conflict zone. This way CAVs are able to maintain safety while using mild control actions that benefit both the CAVs as well as the surrounding human-dominated traffic. Requirements for the quality of V2V communications are determined to ensure the performance of the decision making and control algorithms. The results are demonstrated experimentally using real automobiles and class-8 trucks.

Biography: Gabor Orosz received the M.Sc. degree in Engineering Physics from the Budapest University of Technology, Hungary, in 2002 and the Ph.D. degree in Engineering Mathematics from University of Bristol, UK, in 2006. He held postdoctoral positions at the University of Exeter, UK, and at the University of California, Santa Barbara. In 2010, he joined the University of Michigan, Ann Arbor where he is currently an Associate Professor in Mechanical Engineering and in Civil and Environmental Engineering. During 2017-2018 he was a Visiting Professor in Control and Dynamical Systems at the California Institute of Technology. His research interests include nonlinear dynamics and control, time delay systems, and machine learning with applications to connected and automated vehicles, traffic flow, and biological networks. He served as the Program Chair of the 2015 IFAC Workshop on Time Delay Systems and served as the General Chair of the 2019 IAVSD Workshop on Dynamics of Road Vehicles: Connected and Automated Vehicles. Since 2018 he has been serving as an editor for the journal Transportation Research Part C and since 2021 he has been serving as an editor for the IEEE Transactions on Control Systems Technology.

Host: Pierluigi Nuzzo, nuzzo@usc.edu

Webcast: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiA

Location: Online

Audiences: Everyone Is Invited

Contact: Talyia White

• ### AME Seminar

Wed, Mar 03, 2021 @ 03:30 PM - 04:30 PM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: Samantha Daly, University of California at Santa Barbara

Talk Title: Machine Learning for High-Throughput Experiment and Analysis of Processing-Property Relationships

Abstract: Materials have hierarchical and heterogeneous structures that drive their deformation and failure mechanisms. The relationship between structure and behavior -- such as the impact of the microstructure of a polycrystalline metal on twinning, dislocation slip, grain boundary sliding, and multi-crack systems -- includes complex stochastic and deterministic factors whose interactions are under active debate. In this talk, the application of data-driven approaches to microscale displacement data for the high-throughput segmentation, identification, and analysis of twinning in magnesium (a deformation mechanism that is critical to its ductility and forming) will be discussed. This will include an analysis of deformation twinning over thousands of grains per test, including an analysis of the impact of microstructure on the relative activity of specific twin variants (automatically identified from microscale strain fields) and their evolution under load. The newly developed experimental and analytical approaches are length scale independent and material agnostic, and can be modified to identify a range of deformation and failure mechanisms.

Biography: Samantha (Sam) Daly is a Professor in the Department of Mechanical Engineering at the University of California at Santa Barbara. She received her Ph.D. from Caltech in 2007 and subsequently joined the University of Michigan, where she was on the faculty until 2016 prior to her move to UCSB. The Daly group investigates the mechanics of materials, with a focus on fatigue, fracture, creep, composites, multi-functional materials, and new experimental and data-driven approaches for the characterization of processing -“ structure -“ property relationships. Her recognitions include the Experimental Mechanics Best Paper of the Year Award, IJSS Best Paper of the Year Award, DOE Early Career Award, NSF CAREER Award, AFOSR-YIP Award, ASME Eshelby Mechanics Award, Journal of Strain Analysis Young Investigator Award, ASME Orr Award, and Caddell Award. She currently serves on the Executive Board of the Society of Experimental Mechanics, and as an Associate Editor of the journals Applied Mechanics Reviews, Experimental Mechanics, and Strain.

Host: AME Department

Webcast: https://usc.zoom.us/j/92448962089

Location: Online event

Audiences: Everyone Is Invited

Contact: Tessa Yao

• ### CS Colloquium: Abhinav Verma (University of Texas - Austin) - Neurosymbolic Reinforcement Learning

Thu, Mar 04, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Abhinav Verma, University of Texas - Austin

Talk Title: Neurosymbolic Reinforcement Learning

Series: CS Colloquium

Abstract: Recent advances in Artificial Intelligence (AI) have been driven by deep neural networks. However, neural networks have certain well-known flaws: they are difficult to interpret and verify, have high variability, and lack domain awareness. These issues create a deficiency of trust and are hence a significant impediment to the deployment of AI in safety-critical applications. In this talk, I will present work that addresses these drawbacks via neurosymbolic learning in the reinforcement learning paradigm. Neurosymbolic agents combine experience based neural learning with partial symbolic knowledge expressed via programs in a Domain Specific Language (DSL). Using a DSL provides a principled mechanism to leverage high-level abstractionsfor machine learning models, and establishes a synergistic relationship between machine learning and program synthesis.

To overcome the challenges of policy search in non-differentiable program space we introduce a meta-algorithm that is based on mirror descent, program synthesis, and imitation learning. This approach interleaves the use of synthesized symbolic programs to regularize neural learning with the imitation of gradient-based learning to improve the quality of synthesized programs. This perspective allows us to prove robust expected regret bounds and finite-sample guarantees for this algorithm. The theoretical results guaranteeing more reliable learning are accompanied by promising empirical results on complex tasks such as learning autonomous driving agents and generating interpretable programs for behavior annotation.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Abhinav Verma is a PhD Candidate at the University of Texas at Austin, where he is advised by Swarat Chaudhuri. His research lies at the intersection of machine learning and formal methods, with a focus on building intelligent systems that are reliable, transparent, and secure. His work builds connections between the symbolic reasoning and inductive learning paradigms of artificial intelligence. He is currently supported by a JP Morgan AI Research PhD Fellowship.

Host: Mukund Raghothaman / Bistra Dilkina

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

• ### NL Seminar-LIGHT: Training agents that can act and speak with other models and humans in a rich text adventure game world

Thu, Mar 04, 2021 @ 11:00 AM - 12:00 PM

Information Sciences Institute

Conferences, Lectures, & Seminars

Speaker: Jason Weston , Fair/NYU

Talk Title: LIGHT: Training agents that can act and speak with other models and humans in a rich text adventure game world

Abstract: LIGHT is a rich fantasy text adventure game environment featuring dialogue and actions between agents in the world, which consist of both models and humans. I will summarize work on building this research platform, including crowdsourcing and machine learning to build the rich world environment, training agents to speak and act within it, and deploying the game for lifelong learning of agents by interacting with humans. See
LIGHT Learning in Interactive Games with Humans and Text. The LIGHT project is a large scale fantasy text adventure game research platform for training agents that can both talk and act, interacting either with other models or with humans.
parl. ai and the talk! for more.

Biography: Jason Weston is a research scientist at Facebook, NY and a Visiting Research Professor at NYU. He earned his PhD in machine learning at Royal Holloway, University of London and at AT and T Research in Red Bank, NJ advisors: Alex Gammerman, Volodya Vovk and Vladimir Vapnik in 2000. From 2000 to 2001, he was a researcher at Biowulf technologies. From 2002 to 2003 he was a research scientist at the Max Planck Institute for Biological Cybernetics, Tuebingen, Germany. From 2003 to 2009 he was a research staff member at NEC Labs America, Princeton. From 2009 to 2014 he was a research scientist at Google, NY. His interests lie in statistical machine learning, with a focus on reasoning, memory, perception, interaction and communication. Jason has published over 100 papers, including best paper awards at ICML and ECML, and a Test of Time Award for his work, A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning, ICML 2008 with Ronan Collobert. He was part of the YouTube team that won a National Academy of Television Arts and Sciences Emmy Award for Technology and Engineering for Personalized Recommendation Engines for Video Discovery. He was listed as the 16th most influential machine learning scholar at AMiner and one of the top 50 authors in Computer Science in Science

Host: Jon May and Mozhdeh Gheini

Webcast: This talk will be live streamed only, it will Not Be recorded.

Audiences: Everyone Is Invited

Contact: Petet Zamar

• ### A Virtual Chat with Professor Zeno from the Mork Family Department

Thu, Mar 04, 2021 @ 04:00 PM - 05:00 PM

Viterbi School of Engineering Masters Programs

Conferences, Lectures, & Seminars

Speaker: Wade Zeno, Mork Family Professor

Talk Title: A Virtual Chat with Professor Zeno

Abstract: Sure, they're distinguished and renowned experts in their fields, but Viterbi faculty were once students too. Learn valuable life lessons as they share their professional and personal stories! Together, VGSA and the VASE office presents the Virtual Chat with a Professor Series! These are meant to be informal conversations that you might have with a professor after class or in the hallways. Each session is open to all Viterbi graduate students. Join in to chat with Prof. Mike Gruntman!

Host: VGSA & VASE

Audiences: Everyone Is Invited

Contact: Juli Legat

• ### CS Colloquim: TBA

Fri, Mar 05, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: TBA, TBA

Talk Title: TBA

Series: CS Colloquium

Abstract: TBA

Biography: TBA

Host: Ramakant Nevatia

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

• ### CS Colloquium: Daniel Fried (UC Berkeley) - Learning Grounded Pragmatic Communication

Fri, Mar 05, 2021 @ 12:00 PM - 01:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Daniel Fried, UC Berkeley

Talk Title: Learning Grounded Pragmatic Communication

Series: CS Colloquium

Abstract: To generate language, natural language processing systems predict what to say---why not also predict how listeners will respond? We show how language generation and interpretation across varied grounded domains can be improved through pragmatic inference: explicitly reasoning about the actions and intents of the people that the systems interact with. We train neural generation and interpretation models which ground language into a world context, then layer a pragmatic inference procedure on top of these models. This pragmatic procedure predicts how human listeners will interpret text generated by the models, and reasons counterfactually about why human speakers produced the text they did. We find that this approach improves models' success at generating and interpreting instructions in real indoor environments, as well as in a challenging spatial reference dialogue task.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Daniel Fried is a final-year PhD candidate at UC Berkeley in natural language processing, advised by Dan Klein. His research focuses on language grounding: tying language to world contexts, for tasks like visual- and embodied-instruction following, text generation, and dialogue. Previously, he graduated with an MPhil from the University of Cambridge and a BS from the University of Arizona. His work has been supported by a Google PhD Fellowship, an NDSEG Fellowship, and a Churchill Scholarship.

Host: Xiang Ren

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Mariya Toneva (Carnegie Mellon University) - Data-Driven Transfer of Insight between Brains and AI Systems

Mon, Mar 08, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Mariya Toneva, Carnegie Mellon University

Talk Title: Data-Driven Transfer of Insight between Brains and AI Systems

Series: CS Colloquium

Abstract: Several major innovations in artificial intelligence (AI) (e.g. convolutional neural networks, experience replay) are based on findings about the brain. However, the underlying brain findings took many years to first consolidate and many more to transfer to AI. Moreover, these findings were made using invasive methods in non-human species. For cognitive functions that are uniquely human, such as natural language processing, there is no suitable model organism and a mechanistic understanding is that much farther away.

In this talk, I will present my research program that circumvents these limitations by establishing a direct connection between the human brain and AI systems with two main goals: 1) to improve the generalization performance of AI systems and 2) to improve our mechanistic understanding of cognitive functions. Lastly, I will discuss future directions that build on these approaches to investigate the role of memory in meaning composition, both in the brain and AI. This investigation will lead to methods that can be applied to a wide range of AI domains, in which it is important to adapt to new data distributions, continually learn to perform new tasks, and learn from few samples.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Mariya Toneva is a Ph.D. candidate in a joint program between Machine Learning and Neural Computation at Carnegie Mellon University, where she is advised by Tom Mitchell and Leila Wehbe. She received a B.S. in Computer Science and Cognitive Science from Yale University. Her research is at the intersection of Artificial Intelligence, Machine Learning, and Neuroscience. Mariya works on bridging language in machines with language in the brain, with a focus on building computational models of language processing in the brain that can also improve natural language processing systems.

Host: Yan Liu

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Saiph Savage (University of Washington) - The Future of A.I. for Social Good

Mon, Mar 08, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Saiph Savage, University of Washington

Talk Title: The Future of A.I. for Social Good

Series: CS Colloquium

Abstract: The A.I. industry has powered a futuristic reality of self-driving cars and voice assistants to help us with almost any need. However, the A.I. Industry has also created systematic challenges. For instance, while it has led to platforms where workers label data to improve machine learning algorithms, my research has uncovered that these workers earn less than minimum wage. We are also seeing the surge of A.I. algorithms that privilege certain populations and racially exclude others. If we were able to fix these challenges we could create greater societal justice and enable A.I. that better addresses people's needs, especially groups we have traditionally excluded.

In this talk, I will discuss some of these urgent global problems that my research has uncovered from the A.I. Industry. I will present how we can start to address these problems through my proposed "A.I. For Good" framework. My framework uses value sensitive design to understand people's values and rectify harm. I will present case-studies where I use this framework to design A.I. systems that improve the labor conditions of the workers operating behind the scenes in our A.I. industry; as well as how we can use this framework to safeguard our democracies. I conclude by presenting a research agenda for studying the impact of A.I. in society; and researching effective socio-technical solutions in favor of the future of work and countering techno-authoritarianism.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Saiph Savage conducts research in the intersection of Human Computer Interaction, A.I., and Civic Technology. She is one of the 35 Innovators under 35 by the MIT Technology Review, a Google Anita Borg Scholarship recipient, and a fellow at the Center for Democracy & Technology. Her work has been covered in the BBC, Deutsche Welle, and the New York Times, as well as published in top venues such as ACM CHI, CSCW, and AAAI ICWSM, where she has also won honorable mention awards. Dr. Savage has been awarded grants from the National Science Foundation, the United Nations, industry, and has also formalized new collaborations with Federal and local Governments where she is driving them to adopt Human Centered Design and A.I. to deliver better experiences and government services to citizens. Dr. Savage has opened the research area of Human Computer Interaction at West Virginia University, and Saiph's students have obtained fellowships and internships in industry (Facebook Research, Twitch Research, and Microsoft Research) as well as academia (Oxford Internet Institute). Saiph holds a bachelor's degree in Computer Engineering from the National Autonomous University of Mexico (UNAM), and a master's and Ph.D. in Computer Science from the University of California, Santa Barbara (UCSB). Dr. Savage currently works at the University of Washington; previously she was a Visiting Professor at Carnegie Mellon University (CMU). Additionally, Dr. Savage has been a tech worker at Microsoft Bing, Intel Labs, and a crowd research worker at Stanford.

Host: Bistra Dilkina

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Sanghamitra Dutta (Carnegie Mellon University) - Reliable Machine Learning for High-Stakes Applications: Approaches Using Information Theory

Mon, Mar 08, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Sanghamitra Dutta , Carnegie Mellon University

Talk Title: Reliable Machine Learning for High-Stakes Applications: Approaches Using Information Theory

Series: CS Colloquium

Abstract: How do we make machine learning (ML) algorithms not only ethical, but also intelligible, explainable, and reliable? This is particularly important today as ML enters high-stakes applications such as hiring and education, often adversely affecting people's lives with respect to gender, race, etc. Identifying bias/disparity in a model's decision is often insufficient. We really need to dig deeper and bring in an understanding of anti-discrimination laws. For instance, Title VII of the US Civil Rights Act includes a subtle and important aspect that has implications for the ML models being used today: Disparities in hiring that can be explained by a business necessity are exempt. E.g., disparity arising due to code-writing skills may be deemed exempt for a software engineering job, but the disparity due to an aptitude test may not be (e.g. Griggs v. Duke Power '71). This leads us to a question that bridges the fields of fairness, explainability, and law: How can we identify and explain the sources of disparity in ML models, e.g., did the disparity arise due to the critical business necessities or not? In this talk, I propose the first systematic measure of "non-exempt disparity," i.e., the illegal bias which cannot be explained by business necessities. To arrive at a measure for the non-exempt disparity, I adopt a rigorous axiomatic approach that brings together concepts in information theory, in particular, an emerging body of work called Partial Information Decomposition, with causal inference tools. This quantification allows one to audit a firm's hiring practices, to check if they are compliant with the law. This may also allow one to correct the disparity by better explaining the source of the bias, also providing insights into accuracy-bias tradeoffs.

My research bridges reliability in learning with reliability in computing, which has led to an emerging interdisciplinary area called "coded computing". Towards the end of this talk, I will also provide an overview of some of my results on coded reliable computing that addresses long-standing computational challenges in large-scale distributed machine learning (namely, stragglers, faults, failures) using tools from coding theory, optimization, and queueing.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Sanghamitra Dutta (B. Tech. IIT Kharagpur) is a Ph.D. candidate at Carnegie Mellon University, USA. Her research interests revolve around machine learning, information theory, and statistics. She is currently focused on addressing the emerging reliability issues in machine learning concerning fairness, explainability, and law with recent publications at AAAI'20, ICML'20 (also featured in New Scientist and CMU Engineering News). In her prior work, she has also examined problems in reliable computing, proposing novel algorithmic solutions for large-scale distributed machine learning in the presence of faults and failures, using tools from coding theory (an emerging area called "coded computing"). Her results on coded computing address problems that have been open for several decades and have received substantial attention from across communities (published at IEEE Transactions on Information Theory'19,'20, NeurIPS'16, AISTATS'18, IEEE BigData'18, ICML Workshop Spotlight'19, ISIT'17,'18, Proceedings of IEEE'20 along with two pending patents). She is a recipient of the 2020 Cylab Presidential Fellowship, 2019 K&L Gates Presidential Fellowship, 2019 Axel Berny Presidential Graduate Fellowship, 2017 Tan Endowed Graduate Fellowship, 2016 Prabhu and Poonam Goel Graduate Fellowship, the 2015 Best Undergraduate Project Award at IIT Kharagpur, and the 2014 HONDA Young Engineer and Scientist Award. She has also pursued research internships at IBM Research and Dataminr.

Host: Bistra Dilkina

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Dani Yogatama (DeepMind) - Learning General Language Processing Agents

Tue, Mar 09, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Dani Yogatama, DeepMind

Talk Title: Learning General Language Processing Agents

Series: CS Colloquium

Abstract: The ability to continuously learn and generalize to new problems quickly is a hallmark of general intelligence. Existing machine learning models work well when optimized for a particular benchmark, but they require many in-domain training examples (i.e., input-output pairs that are often costly to annotate), overfit to the idiosyncrasies of the benchmark, and do not generalize to out-of-domain examples. In contrast, humans are able to accumulate task-agnostic knowledge from multiple modalities to facilitate faster learning of new skills.

In this talk, I will argue that obtaining such an ability for a language model requires significant advances in how we acquire, represent, and store knowledge in artificial systems. I will present two approaches in this direction: (i) an information theoretic framework that unifies several representation learning methods used in many domains (e.g., natural language processing, computer vision, audio processing) and allows principled constructions of new training objectives to learn better language representations; and (ii) a language model architecture that separates computation (information processing) in a large neural network and memory storage in a key-value database. I will conclude by briefly discussing a series of future research programs toward building a general linguistically intelligent agent.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Dani Yogatama is a staff research scientist at DeepMind. His research interests are in machine learning and natural language processing. He received his PhD from Carnegie Mellon University in 2015. He grew up in Indonesia and was a Monbukagakusho scholar in Japan prior to studying at CMU.

Host: Xiang Ren

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### Astani Department of Civil and Environmental Engineering Seminar

Tue, Mar 09, 2021 @ 11:00 AM - 12:00 PM

Sonny Astani Department of Civil and Environmental Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Arghavan Louhghalam, Assistant Professor, University of Massachusetts Dartmouth

Talk Title: Physics-based and Data-driven Modeling from eco-friendly roadway network to infrastructure resilience analytics

Abstract: Development of sustainable and resilient infrastructure systems requires novel frameworks that leverage the explosion of data available through advances in sensors, internet, mobility as well as computational models to design for and respond to the challenges of 21st century. In this talk, I will showcase how physics-constrained data-driven modeling enables development of quantitative platforms for identification, monitoring and projection of infrastructure performance. In the first part of the presentation I will describe a citizen-enabled framework to monitor, in real-time, road surface condition, vehicle excess energy consumption, and the related environmental impact at network scale. Unlike the widely used approaches for road infrastructure monitoring that rely solely on data and empirical models, this framework integrates physics-compatible models of road-vehicle interaction with crowdsourced data to characterize the parameters of system. The proposed data-centric platform has the potential to not only help transportation authorities make optimal decisions in the allocation of resources to road maintenance but also guide route selection by individual drivers or fleet owners. This will be a key player in a rapidly evolving world where an accelerating climate change is pressing for dramatic measures to reduce carbon footprint and GHG emissions. The second part of this talk will be focused on modeling damage using an energy-based formulation of lattice element method (LEM). I will describe the potential of mean force (PMF) approach, widely used in statistical physics and introduce a hybrid PMF formulation of LEM to efficiently model fracture and crack growth in heterogenous media. The framework is validated and utilized for meso-scale simulations to estimate the effective fracture properties of heterogeneous materials. The hybrid approach is shown to be a viable choice due to its flexibility in modeling discontinuity and its computational efficiency and reliable results. Finally, I will discuss our efforts to leverage the versatility of this framework and adapt the formulation as a means for efficient characterization of failure and damage in structural systems to establish an efficient quantitative tool for resilience analytics.

Biography: Arghavan Louhghalam is an assistant professor in the department of Civil and Environmental Engineering with a joint appointment in Mechanical Engineering Department at University of Massachusetts, Dartmouth. She also holds a research affiliate position in the department of Civil and Environmental Engineering at MIT. Prior to that she was a postdoctoral research associate at Massachusetts Institute of Technology. She earned her PhD in Engineering Mechanics from the Department of Civil Engineering at the Johns Hopkins University. Her research interests lie in the area of engineering mechanics, physics-constrained data-driven modeling, and applied statistics with particular emphasis on development of smart solutions for resilient and sustainable built environment. Dr Louhghalam is a recipient of NSF early CAREER award and her research on citizen-enabled crowdsourced monitoring of transportation infrastructure has been recognized nationally and featured in media outlets such as the New York Times.

Host: Dr. Roger Ghanem

Location: Zoom: https://usc.zoom.us/j/97228056404; Meeting ID: 972 2805 6404: Passcode: 864779

Audiences: Everyone Is Invited

Contact: Evangeline Reyes

• ### CS Colloquium: Ranjay Krishna (Stanford University) - Visual Intelligence from Human Learning

Tue, Mar 09, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Ranjay Krishna , Stanford University

Talk Title: Visual Intelligence from Human Learning

Series: CS Colloquium

Abstract: At the core of human development is the ability to adapt to new, previously unseen stimuli. We comprehend new situations as a composition of previously seen information and ask one another for clarification when we encounter new concepts. Yet, this ability to go beyond the confounds of their training data remains an open challenge for artificial intelligence agents. My research designs visual intelligence to reason over new compositions and acquire new concepts by interacting with people. My talk will explore these challenges and present the two following lines of work:
First, I will introduce scene graphs, a cognitively-grounded, compositional visual representation. I will discuss how to integrate scene graphs into a variety of computer vision tasks, enabling models to generalize to novel compositions from a few training examples. Since our introduction of scene graphs, the Computer Vision community has developed hundreds of scene graph models and utilized scene graphs to achieve state-of-the-art results across multiple core tasks, including object localization, captioning, image generation, question answering, 3D understanding, and spatio-temporal action recognition.
Second, I will introduce a framework for socially situated learning. This framework pushes agents beyond traditional computer vision training paradigms and enables learning from human interactions in online social environments. I will showcase a real-world deployment of our agent, which learned to acquire new visual concepts by asking people targeted questions on social media. By interacting with over 230K people over 8 months, our agent learned to recognize hundreds of new concepts. This work demonstrates the possibility for agents to adapt and self-improve in real-world social environments.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Ranjay Krishna is a 5th-year Ph.D. candidate at Stanford University, where he is co-advised by Fei-Fei Li and Michael Bernstein. His research lies at the intersection of computer vision and human-computer interaction; it draws on ideas from behavioral and social sciences to improve visual intelligence. His work has been recognized by the Christofer Stephenson Memorial award, as an Accell Innovation Scholar and by two Brown Institute for Media Innovation grants. His work has also been featured in Forbes magazine and in a PBS NOVA documentary. During his Ph.D., he re-designed Stanford's undergraduate Computer Vision course and currently also instructs the graduate Computer Vision course, Stanford's second largest course. He has a M.Sc. from Stanford University. Before that, he conferred a B.Sc. with a double major in Electrical Engineering and in Computer Science from Cornell University. In the past, he has interned at Google AI, Facebook AI Research, and Yahoo Research.

Host: Ramakant Nevatia

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### Optomechanical Manipulation Enabled by Photonic Metasurfaces

Tue, Mar 09, 2021 @ 01:00 PM - 02:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Ognjen Ilic, Professor University of Minnesota

Talk Title: Optomechanical Manipulation Enabled by Photonic Metasurfaces

Series: Photonics Seminar

Host: Electrical and Computer Engineering: Wade Hsu, Mercedeh Khajavikhan, Michelle Povinelli, Constantine Sideris, and Wei Wu

Audiences: Everyone Is Invited

Contact: Jennifer Ramos/Electrophysics

• ### ISE 651 - Epstein Seminar

Tue, Mar 09, 2021 @ 03:30 PM - 04:50 PM

Daniel J. Epstein Department of Industrial and Systems Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Junyi Liu, Postdoctoral Associate, Epstein Dept. of Industrial & Systems Engineering, USC

Talk Title: Nonconvex and Nonsmooth Stochastic Optimization With Modern Applications

Host: Prof. Jong-Shi Pang

Location: Online/Zoom

Audiences: Everyone Is Invited

Contact: Grace Owh

• ### CS Distinguished Lecture: Jure Leskovec (Stanford University) - Mobility Networks for Modeling the Spread of COVID-19: Explaining Inequities and Informing Reopening

Tue, Mar 09, 2021 @ 04:00 PM - 05:20 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Jure Leskovec, Stanford University

Talk Title: Mobility Networks for Modeling the Spread of COVID-19: Explaining Inequities and Informing Reopening

Series: Computer Science Distinguished Lecture Series

Abstract: The COVID-19 pandemic dramatically changed human mobility patterns, necessitating epidemiological models which capture the effects of changes in mobility on virus spread. We introduce a metapopulation SEIR model that integrates fine-grained, dynamic mobility networks to simulate the spread of SARS-CoV-2 in 10 of the largest US metropolitan statistical areas. Derived from cell phone data, our mobility networks map the hourly movements of 98 million people from neighborhoods (census block groups, or CBGs) to points of interest (POIs) such as restaurants and religious establishments, connecting 57k CBGs to 553k POIs with 5.4 billion hourly edges. We show that by integrating these networks, a relatively simple SEIR model can accurately fit the real case trajectory, despite substantial changes in population behavior over time. Our model predicts that a small minority of "superspreader" POIs account for a large majority of infections and that restricting maximum occupancy at each POI is more effective than uniformly reducing mobility. Our model also correctly predicts higher infection rates among disadvantaged racial and socioeconomic groups solely from differences in mobility: we find that disadvantaged groups have not been able to reduce mobility as sharply, and that the POIs they visit are more crowded and therefore higher-risk. By capturing who is infected at which locations, our model supports detailed analyses that can inform more effective and equitable policy responses to COVID-19.

Register in advance for this webinar at:

https://usc.zoom.us/webinar/register/WN_UD7zYBdETsCyLBOiv2DoLw

After registering, attendees will receive a confirmation email containing information about joining the webinar.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Jure Leskovec is Associate Professor of Computer Science at Stanford University, Chief Scientist at Pinterest, and investigator at Chan Zuckerberg Biohub. Dr. Leskovec was the co-founder of a machine learning startup Kosei, which was later acquired by Pinterest. His research focuses on machine learning and data mining large social, information, and biological networks. Computation over massive data is at the heart of his research and has applications in computer science, social sciences, marketing, and biomedicine. This research has won several awards including a Lagrange Prize, Microsoft Research Faculty Fellowship, the Alfred P. Sloan Fellowship, and numerous best paper and test of time awards. It has also been featured in popular press outlets such as the New York Times and the Wall Street Journal. Leskovec received his bachelor's degree in computer science from University of Ljubljana, Slovenia, PhD in machine learning from Carnegie Mellon University and postdoctoral training at Cornell University. You can follow him on Twitter at @jure.

Host: Xiang Ren

Webcast: https://usc.zoom.us/webinar/register/WN_UD7zYBdETsCyLBOiv2DoLw

Location: Online Zoom Webinar

Audiences: Everyone Is Invited

Contact: Computer Science Department

• ### Mork Family Department Spring Virtual Seminars - Jiefei Zhang

Tue, Mar 09, 2021 @ 04:00 PM - 05:20 PM

Mork Family Department of Chemical Engineering and Materials Science

Conferences, Lectures, & Seminars

Speaker: Jiefei Zhang, University of Southern California

Talk Title: A NEW PARADIGM FOR ON-CHIP SCALABLE QUANTUM PHOTONICS

Abstract: ZOOM MEETING INFO:
https://usc.zoom.us/j/98225952695?pwd=d0NMenhCNkliR1ZIR1lBamRpZHh1UT09
Meeting ID: 982 2595 2695 • Passcode: 322435

Host: Andrea Hodge

Audiences: Everyone Is Invited

Contact: Greta Harrison

• ### CS Colloquium: Hongyang Zhang (Toyota Technological Institute) - New Advances in (Adversarially) Robust and Secure Machine Learning

Wed, Mar 10, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Hongyang Zhang , Toyota Technological Institute

Series: CS Colloquium

Abstract: Deep learning models are often vulnerable to adversarial examples. In this talk, we will focus on robustness and security of machine learning against adversarial examples. There are two types of defenses against such attacks: 1) empirical and 2) certified adversarial robustness.

In the second part of the talk, to equip empirical robustness with certification, we study certified adversarial robustness by random smoothing. On one hand, we show that random smoothing on the TRADES-trained classifier achieves SOTA certified robustness when the perturbation radius is small. On the other hand, when the perturbation is large, i.e., independent of inverse of input dimension, we show that random smoothing is provably unable to certify L_infty robustness for arbitrary random noise distribution. The intuition behind our theory reveals an intrinsic difficulty of achieving certified robustness by "random noise based methods", and inspires new directions as potential future work.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Hongyang Zhang is a Postdoc fellow at Toyota Technological Institute at Chicago, hosted by Avrim Blum and Greg Shakhnarovich. He obtained his Ph.D. from CMU Machine Learning Department in 2019, advised by Maria-Florina Balcan and David P. Woodruff. His research interests lie in the intersection between theory and practice of machine learning, robustness and AI security. His methods won the championship or ranked top in various competitions such as the NeurIPS'18 Adversarial Vision Challenge (all three tracks), the Unrestricted Adversarial Examples Challenge hosted by Google, and the NeurIPS'20 Challenge on Predicting Generalization of Deep Learning. He also authored a book in 2017.

Host: David Kempe

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar

Wed, Mar 10, 2021 @ 02:00 PM - 03:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Somil Bansal, Department of Electrical Engineering and Computer Sciences, University of California, Berkeley

Talk Title: Safe and Data-efficient Learning for Robotics

Series: Center for Cyber-Physical Systems and Internet of Things

Abstract: For successful integration of autonomous systems such as drones and self-driving cars in our day-to-day life, they must be able to quickly adapt to ever-changing environments, and actively reason about their safety and that of other users and autonomous systems around them. Even though control-theoretic approaches have been used for decades now for the control and safety analysis of autonomous systems, these approaches typically operate under the assumption of a known system dynamics model and the environment in which the system is operating. To overcome these challenges, machine learning approaches have been explored to operate autonomous systems intelligently and reliably in unpredictable environments based on prior data. However, learning techniques widely used today are extremely data inefficient, making it challenging to apply them to real-world physical systems. Moreover, they lack the necessary mathematical framework to provide guarantees on correctness, causing safety concerns as data-driven physical systems are integrated in our society.

In this talk, we will present a toolbox of methods combining robust optimal control with data-driven techniques inspired by machine learning, to enable performance improvement while maintaining safety. In particular, we design modular architectures that combine system dynamics models with modern learning-based perception approaches to solve challenging perception and control problems in a priori unknown environments in a data-efficient fashion. These approaches are demonstrated on a variety of ground robots navigating in unknown buildings around humans based only on onboard visual sensors. Next, we discuss how we can use optimal control methods not only for data-efficient learning, but also to monitor and recognize the learning system's failures, and to provide online corrective safe actions when necessary. This allows us to provide safety assurances for learning-enabled systems in unknown and human-centric environments, which has remained a challenge to date.

Biography: Somil Bansal completed his MS and PhD in the Electrical Engineering and Computer Sciences Department at the University of California, Berkeley in 2014 and 2020 respectively, and received his B.Tech. in Electrical Engineering from Indian Institute of Technology, Kanpur in 2012. He is currently spending a year as a research scientist at Waymo. In Fall 2021, he will join as an Assistant Professor in the Department of Electrical and Computer Engineering at the University of Southern California, Los Angeles. His research interests include developing mathematical tools and algorithms for control and analysis of autonomous systems, with a focus on bridging learning and control-theoretic approaches for safety-critical autonomous systems. Somil has received several awards, most notably the Eli Jury award and the outstanding graduate student instructor award at UC Berkeley, and the academic excellence award at IIT Kanpur.

Host: Pierluigi Nuzzo, nuzzo@usc.edu

Webcast: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiA

Location: Online

Audiences: Everyone Is Invited

Contact: Talyia White

• ### AME Seminar

Wed, Mar 10, 2021 @ 03:30 PM - 04:30 PM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: George Park, University of Pennsylvania

Talk Title: Toward Predictive Yet Affordable Computations of Practical Wall-Bounded Turbulent Flows

Abstract: Kinetic energy of turbulence is generated at large scales controlled by boundary conditions, but it is dissipated into heat at the smallest scales. The ratio of these two length scales increases rapidly with Reynolds number. Solid walls add another dimension in this scale landscape, where the scale separation gets progressively less pronounced toward the wall. This has significant ramifications on the cost of scale-resolving simulation of practical engineering flows, such as those found in aircraft, wind turbines, and ship hydrodynamics. Direct approaches with full resolution of length and times scales close to the wall are still infeasible with current computing power. The demand for superior designs at reduced cost has led researchers to explore alternative computational approaches that have potential to be predictive yet affordable. Large-eddy simulation (LES) is one such approach where only the energy-containing scales are resolved directly, and the effect of the unresolved motions are modeled. In practical LES calculations, subgrid-scale (SGS) models are used in conjunction with wall models to augment the turbulent shear stress, which otherwise is underpredicted on coarse grids and leads to inaccurate prediction of mean and turbulence quantities.
In this talk, I will discuss the research in my group on this wall-modeled LES approach. Widely used wall-modeling techniques will be discussed with their applications to canonical and complex wall-bounded flows. Challenges in robust and efficient implementation of the models in flow solvers for handling practical geometries will be discussed. I will also highlight recent work to predict flow over realistic aircraft geometries at flight conditions and a boundary layer with mean three dimensionality.

Biography: George Park is an Assistant Professor of Mechanical Engineering and Applied Mechanics at the University of Pennsylvania. He received his Ph.D. and M.S. in Mechanical Engineering (ME) from Stanford University in 2014 and 2011, respectively, and his B.S. in ME from Seoul National University, South Korea in 2009. He worked as a postdoctoral fellow and an engineering research associate at the Center for Turbulence Research (Stanford) prior to joining UPenn as a faculty member in 2018. His research interests include high-fidelity numerical simulation of complex wall-bounded turbulent flows, computational methods with unstructured grids, non-equilibrium turbulent boundary layers, and fluid-structure interaction.

Host: AME Department

Webcast: https://usc.zoom.us/j/97491401429

Location: Online event

Audiences: Everyone Is Invited

Contact: Tessa Yao

• ### CS Colloquium: Vered Shwartz (University of Washington) - Commonsense Knowledge and Reasoning in Natural Language

Wed, Mar 10, 2021 @ 04:00 PM - 05:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Vered Shwartz, University of Washington

Talk Title: Commonsense Knowledge and Reasoning in Natural Language

Series: CS Colloquium

Abstract: Natural language understanding models are trained on a sample of the situations they may encounter. Commonsense and world knowledge, and language understanding and reasoning abilities can help them address unknown situations sensibly. This talk will discuss several lines of work addressing commonsense knowledge and reasoning in natural language. First, I will introduce a new paradigm for commonsense reasoning tasks with introspective knowledge discovery through a process of self-asking information seeking questions ("what is the definition of...") and answering them. Second, I will present work on nonmonotonic reasoning in natural language, a core human reasoning ability that has been studied in classical AI but mostly overlooked in modern NLP, including abductive reasoning (reasoning about plausible explanations), counterfactual reasoning (what if?) and defeasible reasoning (updating beliefs given additional information). Next, I will discuss how generalizing existing knowledge can help language understanding, and demonstrate it for noun compound paraphrasing (e.g. olive oil is "oil made of olives"). I will conclude with open problems and future directions in language, knowledge, and reasoning.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Vered Shwartz is a postdoctoral researcher at the Allen Institute for AI (AI2) and the Paul G. Allen School of Computer Science & Engineering at the University of Washington, working with Yejin Choi. Vered's research interests are in NLP, AI, and machine learning, particularly focusing on commonsense knowledge and reasoning, computational semantics, discourse and pragmatics. Previously, Vered completed her PhD in Computer Science from Bar-Ilan University, under the supervision of Ido Dagan. Vered's work has been recognized with several awards, including The Eric and Wendy Schmidt Postdoctoral Award for Women in Mathematical and Computing Sciences, the Clore Foundation Scholarship, and an ACL 2016 outstanding paper award.

Host: Xiang Ren

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Gedas Bertasius (Facebook AI) - Designing Video Models for Human Behavior Understanding

Thu, Mar 11, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Talk Title: Designing Video Models for Human Behavior Understanding

Series: CS Colloquium

Abstract: Many modern computer vision applications require extracting core attributes of human behavior such as attention, action, or intention. Extracting such behavioral attributes requires powerful video models that can reason about human behavior directly from raw video data. To design such models we need to answer the following three questions: how do we (1) model videos, (2) learn from videos, and lastly, (3) use videos to predict human behavior?

In this talk I will present a series of methods to answer each of these questions. First, I will introduce TimeSformer, the first convolution-free architecture for video modeling built exclusively with self-attention. It achieves the best reported numbers on major action recognition benchmarks while also being more efficient than state-of-the-art 3D CNNs. Afterwards, I will present COBE, a new large-scale framework for learning contextualized object representations in settings involving human-object interactions. Our approach exploits automatically-transcribed speech narrations from instructional YouTube videos, and it does not require manual annotations. Lastly, I will introduce a self-supervised learning approach for predicting a basketball player's future motion trajectory from an unlabeled collection of first-person basketball videos.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Gedas Bertasius is a postdoctoral researcher at Facebook AI working on computer vision and machine learning problems. His current research focuses on topics of video understanding, first-person vision, and multi-modal deep learning. He received his Bachelors Degree in Computer Science from Dartmouth College, and a Ph.D. in Computer Science from the University of Pennsylvania. His recent work was nominated for the CPVR 2020 best paper award.

Host: Ramakant Nevatia

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Jiaming Song (Stanford University) - Beyond Function Approximation: Compression, Inference, and Generation via Supervised Learning

Thu, Mar 11, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Jiaming Song, Stanford University

Talk Title: Beyond Function Approximation: Compression, Inference, and Generation via Supervised Learning

Series: CS Colloquium

Abstract: Supervised learning methods have advanced considerably thanks to deep function approximators. However, important problems such as compression, probabilistic inference, and generative modeling cannot be directly addressed by supervised learning. At the core, these problems involve estimating (and optimizing) a suitable notion of distance between two probability distributions, which is challenging in high-dimensional spaces. In this talk, I will propose techniques to estimate and optimize divergences more effectively by leveraging advances in supervised learning. I will describe an algorithm for estimating mutual information that approaches a fundamental limit of all valid lower bound estimators and can empirically compress neural networks by up to 70% without losing accuracy. I will also show how these techniques can be used to accelerate probabilistic inference algorithms that have been developed for decades by nearly 10x, improve generative modeling and infer suitable rewards for sequential decision making.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Jiaming Song is a fifth-year Ph.D. candidate in the Computer Science Department at Stanford University, advised by Stefano Ermon. His research focuses on learning and inference algorithms for deep probabilistic models with applications in unsupervised representation learning, generative modeling, and inverse reinforcement learning. He received his B.Eng degree in Computer Science from Tsinghua University in 2016. He was a recipient of the Qualcomm Innovation Fellowship.

Host: Bistra Dilkina

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Swabha Swayamdipta (Allen Institute for AI) - Addressing Biases for Robust, Generalizable AI

Thu, Mar 11, 2021 @ 04:00 PM - 05:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Swabha Swayamdipta, Allen Institute for AI

Talk Title: Addressing Biases for Robust, Generalizable AI

Series: CS Colloquium

Abstract: Artificial Intelligence has made unprecedented progress in the past decade. However, there still remains a large gap between the decision-making capabilities of humans and machines. In this talk, I will investigate two factors to explain why. First, I will discuss the presence of undesirable biases in datasets, which ultimately hurt generalization. I will then present bias mitigation algorithms that boost the ability of AI models to generalize to unseen data. Second, I will explore task-specific prior knowledge which aids robust generalization, but is often ignored when training modern AI architectures. Throughout this discussion, I will focus my attention on language applications, and will show how certain underlying structures can provide useful inductive biases for inferring meaning in natural language. I will conclude with a discussion of how the broader framework of dataset and model biases will play a critical role in the societal impact of AI, going forward.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Swabha Swayamdipta is a postdoctoral investigator at the Allen Institute for AI, working with Yejin Choi. Her research focuses on natural language processing, where she explores dataset and linguistic structural biases, and model interpretability. Swabha received her Ph.D. from Carnegie Mellon University, under the supervision of Noah A. Smith and Chris Dyer. During most of her Ph.D. she was a visiting student at the University of Washington. She holds a Masters degree from Columbia University, where she was advised by Owen Rambow. Her research has been published at leading NLP and machine learning conferences, and has received an honorable mention for the best paper at ACL 2020.

Host: Xiang Ren

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### AME PhD Student Seminar

Fri, Mar 12, 2021 @ 03:00 PM - 04:00 PM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: Samuel Goldman, USC AME PhD Student

Talk Title: A Case Study of the Failure of a Compression Spring in a Lunar Percussion Mechanism

Abstract: The Regolith and Ice Drill for the Exploration of New Terrains (TRIDENT) is a rotary-percussive drill being used on several upcoming Lunar exploration programs. Life testing of this drill resulted in the unexpected early failure of a critical compression spring, which cannot be explained by quasi-static analysis. The purpose of this work is to determine if transient dynamic behavior resulting from percussion can explain this failure. An experiment is conducted comparing the effect of various types of spacers, and it is found that a neoprene spacer allows the spring to survive more than twice as many cycles compared to metallic spacers. Additionally, the dynamic response of this system to impact is modeled using the Distributed Transfer Function Method (DTFM), and is compared to FEA and discrete element techniques. It is found that DTFM is capable of bounding the response as computed by FEA, while the discrete element model underestimates peak shear stress by more than 25% in boundary coils. FEA and DTFM both show that wave propagation within the spring could result in peak shear stresses in boundary coils that are over 20% higher than middle coils. These results suggest that percussive wave propagation can explain the early failure of this spring.

Biography: Sam Goldman is a Ph.D. student under Dr. Flashner. His research focus is primarily in modeling and experimentation of percussion mechanisms used in extraterrestrial geotechnical tools. Sam has a B.S. in Biomedical Engineering from The Ohio State University, and an M.S. in Aerospace & Mechanical Engineering from USC.

Host: AME Department

Audiences: Everyone Is Invited

Contact: Christine Franks

• ### CS Colloquium: Amy Zhang (McGill University) - Exploiting latent structure and bisimulation metrics for better generalization in reinforcement learning

Mon, Mar 15, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Amy Zhang, McGill University

Talk Title: Exploiting latent structure and bisimulation metrics for better generalization in reinforcement learning

Series: CS Colloquium

Abstract: The advent of deep learning has shepherded unprecedented progress in various fields of machine learning. Despite recent advances in deep reinforcement learning (RL) algorithms, however, there is no method today that exhibits anywhere near the generalization that we have seen in computer vision and NLP. Indeed, one might ask whether deep RL algorithms are even capable of the kind of generalization that is needed for open-world environments. This challenge is fundamental and will not be solved with incremental algorithmic advances.

In this talk, we propose to incorporate different assumptions that better reflect the real world and allow the design of novel algorithms with theoretical guarantees to address this fundamental problem. We first present how state abstractions can accelerate reinforcement learning from rich observations, such as images, without relying either on domain knowledge or pixel-reconstruction. Our goal is to learn state abstractions that both provide for effective downstream control and invariance to task-irrelevant details. We use bisimulation metrics to quantify behavioral similarity between states, and learn robust latent representations which encode only the task-relevant information from observations. We provide theoretical guarantees for the learned approximate abstraction and extend this notion to families of tasks with varying dynamics.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: I am a final year PhD candidate at McGill University and the Mila Institute, co-supervised by Profs. Joelle Pineau and Doina Precup. I am also a researcher at Facebook AI Research. My work focuses on bridging theory and practice through learning approximate state abstractions and learning representations for generalization in reinforcement learning. I previously obtained an M.Eng. in EECS and dual B.Sci. degrees in Mathematics and EECS from MIT.

Host: Sven Koenig

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Mai ElSherief (Georgia Institute of Technology) - Computational Methods for Identifying Deviant Content in Online Media Ecosystems

Mon, Mar 15, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Mai ElSherief, Georgia Institute of Technology

Talk Title: Computational Methods for Identifying Deviant Content in Online Media Ecosystems

Series: CS Colloquium

Abstract: In recent years, the pervasive adoption of social media has created an ecosystem populated by a pandemonium of opinion, true and false information, and an unprecedented quantity of data on many topics. While online information ecosystems provide freedom of expression and give voice to individuals, they have also suffered a wave of disorder due to the prevalence of malevolent online misuse, manifested as online harassment, cyberbullying, and hate speech; and online misinformation, such as fake news and medical misinformation movements. In this talk, I will present language-centric approaches for improving online hate speech detection and characterization. I will then showcase a human-machine mixed-initiative that aims at investigating and detecting online misinformation surrounding Opioid Use Disorders in collaboration with the Centers for Disease Control and Prevention.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Mai ElSherief is a Postdoctoral Fellow at the School of Interactive Computing at Georgia Tech. Her research interests lie at the intersection of Social Computing, Natural Language Processing, and Online Social Networks, specifically causes of social good. In her research, she adopts Natural Language Processing and Machine Learning methods to examine human behavior pertaining to online abuse, biases, public health intelligence, and community wellbeing. Prior to her Postdoctoral Fellowship, she received Ph.D. from the Computer Science department at UC, Santa Barbara within the Mobility Management and Networking (MOMENT) Lab along with a Certificate in College and University Teaching (CCUT) to demonstrate superior competence and experience in preparation for teaching at the university or college level.

Her research on computationally understanding the psychological impacts of active shooting drills on K-12 school communities received press coverage by NBC, the Hill, and 11Alive. She has been a summer research intern at the Berkman Klein Center for Internet and Society at Harvard University understanding anti-immigration sentiment and the discursive practices of online hate groups. She has been selected as a 2020 UC Berkley EECS Rising Stars Participant. She was also awarded the UCSB 2019 CS Outstanding Graduate Student and the 2017 Fiona and Michael Goodchild Graduate mentoring award for her distinguished research mentoring of undergraduate students.

Host: Bistra Dilkina

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### CS Colloquium: Dhanya Sridhar (Columbia University) - Beyond prediction: NLP for causal inference

Tue, Mar 16, 2021 @ 09:00 AM - 10:00 AM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Dhanya Sridhar, Columbia University

Talk Title: Beyond prediction: NLP for causal inference

Series: CS Colloquium

Abstract: Why do some misleading articles go viral? Does partisan speech affect how people behave? Many pressing questions require understanding the effects of language. These are causal questions: did an article's writing style cause it to go viral or would it have gone viral anyway? With text data from social media and news sites, we can build predictors with natural language processing (NLP) techniques but these methods can confuse correlation with causation. In this talk, I discuss my recent work on NLP methods for making causal inferences from text. Text data present unique challenges for disentangling causal effects from non-causal correlations. I present approaches that address these challenges by extending black box and probabilistic NLP methods. I outline the validity of these methods for causal inference, and demonstrate their applications to online forum comments and consumer complaints. I conclude with my research vision for a data analysis pipeline that bridges causal thinking and machine learning to enable better decision-making and scientific understanding.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Dhanya Sridhar is a postdoctoral researcher in the Data Science Institute at Columbia University. She completed her PhD at the University of California Santa Cruz. Her current research is at the intersection of machine learning and causal inference, focusing on applications to social science. Her thesis research focused on probabilistic models of relational data.

Host: Fei Sha

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### Astani Department of Civil and Environmental Engineering Seminar

Tue, Mar 16, 2021 @ 11:00 AM - 12:00 PM

Sonny Astani Department of Civil and Environmental Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Wenjing (Angela) Zhang, Associate Professor, Executive MBA in Management of Technology, Department of Environmental Engineering, Technical University of Denmark

Talk Title: Shaping our water technology by functional materials and electrospinning

Abstract: With the ever-increasing growth of population and advancements in medical treatments, a growing number of contaminants are entering the aqueous environment from human activity. In particular, for industrialized countries, the concerns for public health and environmental impact are exemplified by the widespread use of pharmaceuticals and their significance as contaminants of emerging concerns (CECs). Some of CECs with highly persistent could lead to detrimental effects on survival and growth of aquatic organisms. Conventional municipal wastewater treatment technologies based on activated sludge remains ineffective. Thus, there is an urgent need for a sustainable and effective wastewater treatment technology to remediate water.

In this talk, I would like to introduce the research projects where we combine functional material synthesis and electrospinning to structure the adsorbents/catalysts into a hiarchiary 3-dimentional reactor. By harvesting solar or mechanical energies, we are able to capture and degrade the contaminants while the clean water flows through.

Biography: Dr. Wenjing (Angela) Zhang is an Associate Professor and leader of Advanced material and membrane research group in the Department of Environmental Engineering at Technical University of Denmark (DTU). Currently she has 9 Postdoc/PhD students in her research group with state-of-art facilities in the fields of catalyst synthesis, electrospinning, solution plasma, electrochemistry, photocatalytic chemistry and membrane filtration. She received her MSc in Mechanical Engineering in 2005 and Ph.D. in Chemical Engineering in 2009 at Hong Kong University of Science and Technology (HKUST). Prior to joining DTU, she was a Research Associate at Vanderbilt University in the United States for 3 years, where she obtained substantial experience in conducting independent award-winning research, mentoring PhD and undergraduate students, writing successful government subsidy proposals (US Department of Energy) and collaborating on research projects with renowned global companies (3M Corporation and Merck KGaA).

Host: Dr. Amy Childress

Location: Zoom: https://usc.zoom.us/j/97228056404; Meeting ID: 972 2805 6404: Passcode: 864779

Audiences: Everyone Is Invited

Contact: Evangeline Reyes

• ### CS Colloquium: Aloni Cohen (Boston University) - Bridging the Divide Between Computer Science and Law

Tue, Mar 16, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Aloni Cohen , Boston University

Talk Title: Bridging the Divide Between Computer Science and Law

Series: CS Colloquium

Abstract: Seriously engaging with law and policy exposes new computer science research directions that also have policy consequences. My work aims to understand and resolve the tensions between the theory of privacy and cryptography on the one hand and the privacy laws that govern its eventual real-world context. In this talk, I'll describe work that tackles three broad questions: How can we bridge the basic concepts of data privacy in computer science and law? How can privacy theory have a positive impact on policy? How can we incorporate legal powers and constraints into our cryptographic threat models for better cryptography?

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Aloni Cohen a Postdoctoral Associate at Boston University, with a joint appointment at the Hariri Institute for Computing and the School of Law. His research explores the interplay between theoretical cryptography, privacy, law, and policy. Aloni earned his PhD in electrical engineering and computer science at MIT where he was advised by Shafi Goldwasser and supported by a Facebook Fellowship and an NSF Graduate Student Fellowship. Aloni is a former affiliate at the Berkman Klein Center for Internet & Society and a Fellow at the Aspen Tech Policy Hub.

Host: Aleksandra Korolova

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### ISE 651 - Epstein Seminar

Tue, Mar 16, 2021 @ 03:30 PM - 04:50 PM

Daniel J. Epstein Department of Industrial and Systems Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Suvrajeet Sen, Professor

Talk Title: TBD

Host: Prof. Jong-Shi Pang

Location: Online/Zoom

Audiences: Everyone Is Invited

Contact: Grace Owh

• ### Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar

Wed, Mar 17, 2021 @ 02:00 PM - 03:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Hamed Mohsenian-Rad, Electrical & Computer Engineering and Bourns Family Faculty Fellow, University of California, Riverside

Talk Title: Data-Driven Analysis of Events in Power Distribution Synchrophasors

Series: Center for Cyber-Physical Systems and Internet of Things

Abstract: Synchrophasor measurements offer an unprecedented level of visibility in power distribution infrastructure. These are time-synchronized single-phase or three-phase voltage and current phasor measurements on medium and low voltage distribution circuits. However, data availability alone is not enough to enhance operational intelligence. In this talk, we make the case that the analysis of "events" is a key to translate the data from distribution synchrophasors into useful high-level information. An event in this study is defined rather broadly to include any major change in any component across the distribution feeder. The real data that is used in this study is obtained from a pilot distribution feeder in Riverside, CA. The goal is to enhance situational awareness in distribution grid by keeping track of the operation (or misoperation) of various grid equipment, assets, distribution energy resources, loads, etc. A combination of data-driven machine learning tools and hybrid model-based methodologies are discussed to automatically (and often remotely) detect, classify, and identify the causes of events and their characteristics in power distribution systems. Use cases are diverse and may include asset monitoring, non-intrusive load modeling, analysis of system dynamics, cybersecurity, etc.

Biography: Dr. Hamed Mohsenian-Rad is a Professor of Electrical and Computer Engineering and a Bourns Family Faculty Fellow at the University of California, Riverside. His research interests include developing hybrid data-driven and model-based techniques for monitoring, control, and optimization of power systems and smart grids. He has received the NSF CAREER Award, a Best Paper Award from the IEEE Power and Energy Society (PES) General Meeting, and a Best Paper Award from the IEEE International Conference on Smart Grid Communications. Two of his papers are currently ranked as the two most cited articles in the IEEE Transactions on Smart Grid. Dr. Mohsenian-Rad is the author of a new textbook, Smart Grid Sensors: Principles and Applications by Cambridge University Press. He is the founding Director of the UC-National Lab Center for Power Distribution Cyber Security, a multi-disciplinary cyber-security research initiative across four University of California (UC) campuses and two Department of Energy (DoE) National Labs. He also serves as the Associate Director of the Winston Chung Global Energy Center, an endowed research center in the area of energy and sustainability at UC Riverside. He has served as the PI for over $10 million smart grid research projects. He received his Ph.D. in Electrical and Computer Engineering from the University of British Columbia, Vancouver, Canada in 2008. Dr. Mohsenian-Rad is a Fellow of the IEEE. Host: Pierluigi Nuzzo, nuzzo@usc.edu Webcast: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiA Location: Online Audiences: Everyone Is Invited Contact: Talyia White • ### AME Seminar Wed, Mar 17, 2021 @ 03:30 PM - 04:30 PM Aerospace and Mechanical Engineering Conferences, Lectures, & Seminars Speaker: Morteza Gharib, Caltech Talk Title: Vortex in the Eye: Thermal Effects on Fluid Mixing in the Eye Abstract: Age-related macular degeneration (AMD) is the leading cause of central vision loss in the developed world. Wet AMD can be managed through serial intravitreal injections of anti-vascular endothelial growth factor (anti-VEGF) agents. However, sometimes the treatment is ineffective. Given that the half-life of the drug is limited, inefficient mixing of the injected drug in the vitreous chamber of the eye may contribute to the ineffectiveness. Here, we introduce thermal heating as a means of enhancing the mixing-process in the vitreous chamber and investigate parameters that potentially influence its effectiveness. Our in-vitro studies point to the importance of the location of the heating on the eye. A significant increase in the mixing and delivery of drugs to the targeted area (the macula) could be achieved by placing heating pads so that a current against gravity is induced in the vitreous. The presented results can potentially help in the development of a better strategy for intravitreal injection and improve the quality of patient care. Biography: Mory Gharib is Hans W. Liepmann Professor of Aeronautics and Bioinspired Engineering; Chair of Graduate Aerospace Department (GALCIT); Director of Center for Autonomous Systems and Technologies. He received his B.S. degree in Mechanical Engineering from Tehran University (1975) and his M.S. 1978, in Aerospace and Mechanical Engineering from Syracuse University and his Ph.D.1983, in Aeronautics from Caltech. He joined Caltech as a professor of Aeronautics. Professor Gharib's current research interests in conventional fluid dynamics and aeronautics include Vortex dynamics, active and passive flow control, autonomous flight, and underwater systems. His Biological flows research includes cardiovascular and ophthalmology, and medical devices. Dr. Gharib's honors and affiliations include: Member, American Academy of Arts and Sciences; Member, National Academy of Engineering; Charter Fellow, National Academy of Inventors; Fellow, American Association for the Advancement of Science; Fellow, American Physical Society; Fellow, American Society of Mechanical EngineeringHe has received the G.I. Taylor Medal from the Society of Engineering Sciences, The Fluid Dynamics Prize from the American Physical Society and five new technology recognition awards from NASA in the fields of advanced laser imaging and nanotechnology. In 2008 he received R&D Magazine's "R&D 100 innovation award" for one of the year's best inventions for his 3-D imaging camera system. Additionally, Dr. Gharib has published more than 250 papers in refereed journals and has been issued 120 U.S. Patents. Host: AME Department More Info: https://usc.zoom.us/j/97398164359 Webcast: https://usc.zoom.us/j/97398164359 WebCast Link: https://usc.zoom.us/j/97398164359 Audiences: Everyone Is Invited Contact: Tessa Yao • ### CS Colloquium: Amy Pavel (Carnegie Mellon University / AI/ML Apple) - Human-AI Systems for Creating and Understanding Videos Thu, Mar 18, 2021 @ 11:00 AM - 12:00 PM Computer Science Conferences, Lectures, & Seminars Speaker: Amy Pavel, Carnegie Mellon University / AI/ML Apple Talk Title: Human-AI Systems for Creating and Understanding Videos Series: CS Colloquium Abstract: Video is becoming a core medium for communicating a wide range of content, including educational lectures, vlogs, and how-to tutorials. While videos are engaging and informative, they lack the familiar and useful affordances of text for browsing, skimming,and flexibly transforming information. This severely limits who can interact with video content and how they can interact with it, makes editing a laborious process, and means that much of the information in videos is not accessible to everyone. But, what future systems will make videos useful for all users? In this talk, I'll share my work creating interactive Human-AI systems that combine the benefits of multiple mediums of communication (e.g., text, video, and audio) in two key areas: 1) helping domain experts find content of interest in videos, and 2) making videos accessible to people who are blind or have visual impairments. First, I'll discuss core challenges of finding information in videos from interviews with domain experts and people with disabilities. Then, I will present new systems that leverage AI, and the results of technical and user evaluations that demonstrate system efficacy. I will conclude with how hybrid HCI-AI breakthroughs will make digital communication more effective and accessible in the future, and how new interactions can help us to realize the full potential of recent AI/ML advances. Biography: Amy Pavel is a Postdoctoral Fellow at Carnegie Mellon University and a Research Scientist in AI/ML at Apple. Her research explores AI-driven interactive techniques for making digital communication effective and accessible for all. Her work creating Human-AI systems to improve communication has appeared at ACM/IEEE conferences including UIST, CHI, ASSETS, and VR. She recently served as an associate chair for the UIST and CHI program committees, received 2 best paper nominations at CHI, and was selected as a Rising Star in EECS. She previously received her Ph.D. in Computer Science at UC Berkeley, where her work developing interactive video abstractions was supported by an NDSEG fellowship and an EECS Excellence Award. Read more about her research at: https://urldefense.com/v3/__https://amypavel.com/__;!!LIr3w8kk_Xxm!_kp1txvo_2fY97o1Ag_-lE6oKo_wqfl1jqPYTl7GDZDnH5NsjUdzasIfRnuxsBo$

Host: Heather Culbertson / Bistra Dilkina

Audiences: Everyone Is Invited

Contact: Assistant to CS chair

Fri, Mar 19, 2021 @ 10:00 AM - 11:30 AM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Ming C. Leu, Keith and Pat Bailey Distinguished Professor, Department of Mechanical and Aerospace Engineering, Missouri University of Science and Technology

Abstract: Ceramics are important engineering materials due to their unique properties such as high hardness, high-temperature resistance, and high-corrosion resistance. Additive manufacturing (AM) of ceramic material is difficult and challenging because of the high melting temperature and flaw-sensitive nature of ceramics. However, through intensive research over the past two decades, significant progress on AM of ceramics has been made. This talk will first review different categories of ceramic AM processes and recent technology advances in each category. Comparisons will be made on the advantages and limitations of each ceramic AM process category in terms of part quality, dimensional accuracy, surface finish, and material flexibility. The practical applications of various ceramic AM processes in relation to the characteristics of each process category will be described. A novel extrusion-based AM process, called Ceramic On-Demand Extrusion (CODE), which was developed in recent years by the seminar speakers research group for fabricating ceramic components with near theoretical density will be presented, including choice of support material and part fabrication with multiple and graded materials. Finally, future research needs and innovation opportunities of ceramic AM will be discussed.

Biography: The research interests of Dr Leu include additive manufacturing, 3D printing, intelligent robotics and automation, and cyber-physical manufacturing. He has published over 480 papers in referred professional journals and conference proceedings. Dr. Leu has received numerous professional awards including, among others, the International Freeform and Additive Manufacturing Excellence (FAME) Award (2020), ASME Milton C. Shaw Manufacturing Research Medal (2018), University of Missouri President Leadership Award (2017), ASME Blackall Machine Tool and Gage Award (2014), ISFA Hideo Hanafusa Outstanding Investigator Award (2008), ASME Distinguished Service Award (2004), SME University Lead Award (1994), NJIT Harlan J. Perlis Research Award (1993), NSF Presidential Young Investigator Award (1985), SAE Ralph R. Teetor Education Award (1985), as well as several best paper awards.

Webcast: Please register for this webinar at: https://usc.zoom.us/webinar/register/WN_-jklT28WSJ2J7rGF-jptng

Location: Online event

Audiences: Everyone Is Invited

Contact: Tessa Yao

• ### All-Epitaxial Plasmonic Optoelectronics

Tue, Mar 23, 2021 @ 01:00 PM - 02:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Dan Wasserman, University of Texas Austin

Talk Title: All-Epitaxial Plasmonic Optoelectronics

Series: Photonics Seminar

Host: Electrical and Computer Engineering: Wade Hsu, Mercedeh Khajavikhan, Michelle Povinelli, Constantine Sideris, and Wei Wu

Audiences: Everyone Is Invited

Contact: Jennifer Ramos/Electrophysics

• ### **NO ISE 651 Epstein Seminar - USC WELLNESS DAY**

Tue, Mar 23, 2021 @ 03:30 PM - 04:50 PM

Daniel J. Epstein Department of Industrial and Systems Engineering

Conferences, Lectures, & Seminars

Audiences: Everyone Is Invited

Contact: Grace Owh

• ### CAIS Seminar: Maria Rodriguez (University at Buffalo) - The Root of Algorithmic Bias and How to Deal With it

Wed, Mar 24, 2021 @ 01:00 PM - 02:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Maria Rodriguez, University at Buffalo

Talk Title: The Root of Algorithmic Bias and How to Deal With it

Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series

Abstract: In this talk, Dr. Rodriguez describes what she sees as the central issue undergirding academic conversations concerning bias in algorithmic output. Laying out this cause in plain terms, Dr. Rodriguez offers actionable mitigation strategies for individuals, groups and organizations invested in producing tech solutions for social good.

Register in advance for this webinar at:

https://usc.zoom.us/webinar/register/WN_lgXhhV2zR5ShvC70HyEKUg

After registering, attendees will receive a confirmation email containing information about joining the webinar.

This lecture satisfies requirements for CSCI 591: Research Colloquium.

Biography: Dr. Rodriguez is an Assistant Professor at the School of Social Work, University at Buffalo (SUNY); a Faculty Associate at the BerkmanKlein Center for Internet and Society at Harvard University; a Faculty Fellow at the Center for Democracy and Technology; as well as a member of the Twitter Academic Research Advisory Board. Her work lies at the intersection of computational social science, demography, and social policy.

Host: USC Center for Artificial Intelligence in Society (CAIS)

Webcast: https://usc.zoom.us/webinar/register/WN_lgXhhV2zR5ShvC70HyEKUg

Location: Online Zoom Webinar

Audiences: Everyone Is Invited

Contact: Computer Science Department

• ### AME Seminar

Wed, Mar 24, 2021 @ 03:30 PM - 04:30 PM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: Daniel Bodony, Univ. Illinois Urbana-Champaign

Talk Title: The Fluid Mechanics of Hypersonic Fluid-Structure Interactions

Abstract: The interaction of high-speed aerodynamics with thermo-mechanically compliant structures is a critical design consideration for single-use and reusable hypersonic vehicles. Historical techniques for predicting fluid-thermal-structure interaction (FTSI) are insufficient for envisioned hypersonic flight systems, leading to a resurgent effort towards understanding, modeling, and predicting FTSI-coupled systems. In this talk, we will present the impact of FTSI on two fundamental scenarios -- boundary layer transition and shock-boundary layer interaction -- informed using a combination of stability analyses and direct numerical simulation techniques. In each scenario, focus will be given to the fluid mechanics involved in the fluid-structure coupling. Supporting details on the relevant theoretical and numerical details required for accurate prediction will also be discussed.

Biography: Daniel J. Bodony is the Blue Waters Professor, Donald Biggar Willett Faculty Scholar and Associate Head for Graduate Programs in the Department of Aerospace Engineering at the University of Illinois. He received his Ph.D. in Aeronautics & Astronautics from Stanford University in 2005. After working at the NASA Ames/Stanford Center for Turbulence Research he joined the University of Illinois in late 2006 as an assistant professor. He received an NSF CAREER award in 2012 in Fluid Dynamics, is an Associate Fellow of the AIAA, and received the University of Illinois' Promotion with Distinction Award in 2020

Host: AME Department

Webcast: https://usc.zoom.us/j/91084441303

Audiences: Everyone Is Invited

Contact: Tessa Yao

• ### CS Colloquium: Michał Dereziński (University of California, Berkeley) - Bridging algorithmic and statistical randomness in machine learning

Thu, Mar 25, 2021 @ 11:00 AM - 12:00 PM

Computer Science

Conferences, Lectures, & Seminars

Speaker: Michał Dereziński , University of California, Berkeley

Talk Title: Bridging algorithmic and statistical randomness in machine learning

Series: CS Colloquium

Abstract: Randomness is a key resource in designing efficient algorithms, and it is also a fundamental modeling framework in statistics and machine learning. Methods that lie at the intersection of algorithmic and statistical randomness are at the forefront of modern data science. In this talk, I will discuss how statistical assumptions affect the bias-variance trade-offs and performance characteristics of randomized algorithms for, among others, linear regression, stochastic optimization, and dimensionality reduction. I will also present an efficient algorithmic framework, called joint sampling, which is used to both predict and improve the statistical performance of machine learning methods, by injecting carefully chosen correlations into randomized algorithms.

In the first part of the talk, I will focus on the phenomenon of inversion bias, which is a systematic bias caused by inverting random matrices. Inversion bias is a significant bottleneck in parallel and distributed approaches to linear regression, second order optimization, and a range of statistical estimation tasks. Here, I will introduce a joint sampling technique called Volume Sampling, which is the first method to eliminate inversion bias in model averaging. In the second part, I will demonstrate how the spectral properties of data distributions determine the statistical performance of machine learning algorithms, going beyond worst-case analysis and revealing new phase transitions in statistical learning. Along the way, I will highlight a class of joint sampling methods called Determinantal Point Processes (DPPs), popularized in machine learning over the past fifteen years as a tractable model of diversity. In particular, I will present a new algorithmic technique called Distortion-Free Intermediate Sampling, which drastically reduced the computational cost of DPPs, turning them into a practical tool for large-scale data science.

This lecture satisfies requirements for CSCI 591: Research Colloquium

Biography: Michał Dereziński is a postdoctoral fellow in the Department of Statistics at the University of California, Berkeley. Previously, he was a research fellow at the Simons Institute for the Theory of Computing (Fall 2018, Foundations of Data Science program). He obtained his Ph.D. in Computer Science at the University of California, Santa Cruz, advised by professor Manfred Warmuth, where he received the Best Dissertation Award for his work on sampling methods in statistical learning. Michał's current research is focused on developing scalable randomized algorithms with robust statistical guarantees for machine learning, data science and optimization. His work on reducing the cost of interpretability in dimensionality reduction received the Best Paper Award at the Thirty-fourth Conference on Neural Information Processing Systems. More information is available at: https://users.soe.ucsc.edu/~mderezin/.

Host: David Kempe

Audiences: By invitation only.

Contact: Assistant to CS chair

• ### National Reconnaissance Office (NRO) Career Panel

Fri, Mar 26, 2021 @ 10:00 AM - 11:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: NRO Professionals, NRO Professionals

Talk Title: National Reconnaissance Office (NRO) Career Panel

Host: USC Intelligence Community Center for Academic Excellence (IC CAE)

Audiences: Students and Faculty

Contact: Jennifer Ramos/Electrophysics

• ### Astani Department of Civil and Environmental Engineering Seminar

Tue, Mar 30, 2021 @ 11:00 AM - 12:00 PM

Sonny Astani Department of Civil and Environmental Engineering

Conferences, Lectures, & Seminars

Speaker: Jack W. Baker, Ph.D., Professor, Civil and Environmental Engineering, Stanford University

Talk Title: Simulation of regional post-earthquake recovery for performance-based

Abstract: State of the art performance-based earthquake engineering (PBEE) procedures such as FEMA P-58 generally treat buildings as islands, with respect to modeling regional impacts and post-earthquake recovery. This talk presents an overview of recent research to advance direct simulation of regional impacts and recovery within a PBEE framework. Specifically, work to scale single-building performance-based assessments to a regional scale is demonstrated. Then, refinements to include the impact of damaged roads and neighboring buildings on repair and recovery timelines is presented. Finally,a coupled assessment of economic and physical impacts is illustrated, in order to account for private-sector decision-making and regional industrial capacity constraints on recovery. Collectively, these developments move us closer to regional-scale performance assessments that can incorporate a broader range of factors in forecasts, and thus can support a broader range of decision-making to increase community resilience.

Biography: Professor Baker's work focuses on the development and use of probabilistic and statistical tools for managing risk due to extreme loads on the built environment. He studies risk to spatially distributed systems, characterization of earthquake ground motions, and probabilistic risk assessments for a number of types of structures. Professor Baker joined Stanford in 2006 from the Swiss Federal Institute of Technology (ETH Zurich), where he was a visiting researcher in the Department of Structural Engineering. He has degrees in Structural Engineering (Stanford, M.S. 2002,Ph.D. 2005), Statistics (Stanford, M.S. 2004) and Mathematics and Physics(Whitman College, B.A. 2000). His awards include the Shah Family Innovation Prize from the Earthquake Engineering Research Institute, the CAREER Award from the National Science Foundation, the Early Achievement Research Award from the International Association for Structural Safety and Reliability, the Walter L. Huber Prize from ASCE, the Helmut Krawinkler Award from the Structural Engineers Association of Northern California, and the Eugene L. Grant Award for excellence in teaching from Stanford.

Host: Dr. Roger Ghanem

Location: Zoom: https://usc.zoom.us/j/97228056404; Meeting ID: 972 2805 6404: Passcode: 864779

Audiences: Everyone Is Invited

Contact: Evangeline Reyes

• ### Space-Time Optics: A New Frontier for Structured Light

Tue, Mar 30, 2021 @ 01:00 PM - 02:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Prof. Ayman Abouraddy, University of Central Florida

Talk Title: Space-Time Optics: A New Frontier for Structured Light

Series: Photonics Seminar

Host: Electrical and Computer Engineering: Wade Hsu, Mercedeh Khajavikhan, Michelle Povinelli, Constantine Sideris, and Wei Wu

Audiences: Everyone Is Invited

Contact: Jennifer Ramos/Electrophysics

• ### ISE 651 - Epstein Seminar

Tue, Mar 30, 2021 @ 03:30 PM - 04:50 PM

Daniel J. Epstein Department of Industrial and Systems Engineering

Conferences, Lectures, & Seminars

Speaker: Dr. Roger G. Ghanem, Gordon S. Marshall Professor of Engineering Technology; Professor, Dept. of Civil & Environmental Engineering, USC

Talk Title: Physics, Structure, and Uncertainty: Probabilistic Learning for Risk Mitigation

Abstract:

Host: Prof. Jong-Shi Pang

Location: Online/Zoom

Audiences: Everyone Is Invited

Contact: Grace Owh

• ### Mork Family Department Spring Virtual Seminars - Steve May

Tue, Mar 30, 2021 @ 04:00 PM - 05:20 PM

Mork Family Department of Chemical Engineering and Materials Science

Conferences, Lectures, & Seminars

Speaker: Steve May, Drexler University

Talk Title: ANION-BASED APPROACHES TO ENGINEERING FUNCTIONALITY IN PEROVSKITE OXIDE HETEROSTRUCTURES

Abstract: ZOOM MEETING INFO:
https://usc.zoom.us/j/98225952695?pwd=d0NMenhCNkliR1ZIR1lBamRpZHh1UT09
Meeting ID: 982 2595 2695 • Passcode: 322435

Host: Jay Ravichandran

Audiences: Everyone Is Invited

Contact: Greta Harrison

• ### Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar

Wed, Mar 31, 2021 @ 02:00 PM - 03:00 PM

Ming Hsieh Department of Electrical and Computer Engineering

Conferences, Lectures, & Seminars

Speaker: Necmiye Ozay, Electrical Engineering and Computer Science, University of Michigan

Talk Title: Safety for Autonomous Systems with Information Abundance or Scarcity

Series: Center for Cyber-Physical Systems and Internet of Things

Abstract: Modern autonomous systems, like self-driving cars, unmanned aerial vehicles, or robots, are equipped with advanced sensing, learning, and perception modules. On one hand these modules render the overall system more informed, possibly providing predictions into the future. On the other hand, they can be unreliable, as in the case of vision-based perception algorithms unexpectedly failing to detect the obstacles. In this talk, I will discuss some of our recent work on problems that deal with synthesizing controllers to ensure safety and invariance in the presence of information imperfections or predictions. I will show problem instances in these different information regimes when control synthesis can be achieved in a scalable way. I will also discuss how these ideas can be extended to develop algorithms for corner case generation for testing and falsification purposes.

Biography: Necmiye Ozay received the B.S. degree from Bogazici University, Istanbul in 2004, the M.S. degree from the Pennsylvania State University, University Park in 2006 and the Ph.D. degree from Northeastern University, Boston in 2010, all in electrical engineering. She was a postdoctoral scholar at the California Institute of Technology, Pasadena between 2010 and 2013. She joined the University of Michigan, Ann Arbor in 2013, where she is currently an associate professor of Electrical Engineering and Computer Science. Dr. Ozay's research interests include hybrid dynamical systems, control, optimization and formal methods with applications in cyber-physical systems, system identification, verification & validation, autonomy and dynamic data analysis. Her papers received several awards including a Nonlinear analysis: Hybrid Systems Prize Paper Award for years 2014-2016. She has received the 1938E Award and a Henry Russel Award from the University of Michigan for her contributions to teaching and research, and five young investigator awards, including NSF CAREER.

Host: pierluigi Nuzzo, nuzzo@usc.edu

Webcast: https://usc.zoom.us/webinar/register/WN_Qk4-7AthThudso7LXs2OiA

Location: Online

Audiences: Everyone Is Invited

Contact: Talyia White

• ### AME Seminar

Wed, Mar 31, 2021 @ 03:30 PM - 04:30 PM

Aerospace and Mechanical Engineering

Conferences, Lectures, & Seminars

Speaker: Joanna Austin, Caltech

Talk Title: Hypervelocity Spherically-Blunted Cone Flows in Mars Entry Ground Testing

Abstract: The intent to launch larger vehicles in future Mars missions increases the requirements for ground testing in the high-stagnation enthalpy environment encountered by the vehicle during the hypersonic phase of entry, descent and landing. During atmospheric entry, strong shock compression and high post-shock temperatures lead to significant chemical dissociation and vibrational excitation in the shock layer in front of a sphere-cone capsule, particularly near the stagnation region. For Mars missions, accurate thermochemical modeling of carbon dioxide, a principal component of the atmosphere with complex vibrational energy exchange, is particularly important. We examine the shock layer over sphere and spherically-blunted cone geometries through reacting Navier-Stokes simulations and experiments in two facilities capable of high-stagnation enthalpy, hypersonic flows simulating Mars planetary entry conditions: the T5 Reflected Shock Tunnel and the Hypervelocity Expansion Tube. A recently-developed unified model for sphere and sphere-cone behavior is first verified for high-stagnation enthalpy CO2 flows through simulations with thermal and chemical nonequilibrium. Shock standoff distance measurements in both facilities are in good agreement with model predictions. The need to account for the divergence of the streamlines in conical nozzles is highlighted and an existing model is extended to account for changes in shock curvature between parallel and conical flow. The contributions of vibrational and chemical nonequilibrium to the stagnation line density profile are quantified using the simulation results comparing three chemical kinetic models. Experimental measurement of fore- and aftbody MWIR radiation will also be discussed.

Biography: Joanna Austin is Professor of Aerospace at the Graduate Aerospace Laboratories, California Institute of Technology. She received B.E. (Mechanical and Space Engineering) and B.Sc. (Mathematics) degrees from the University of Queensland, Australia, and M.S. followed by Ph.D. (2003) degrees in Aeronautics from the California Institute of Technology. Austin then joined the faculty in the Aerospace Engineering department at the University of Illinois, becoming Associate Professor and Willett Faculty Scholar, before moving back to Caltech in 2014, where she is a co-PI in the Caltech Hypersonics Group. Austin's research is focused on fundamental problems in reactive, compressible flows across a broad range of applications including hypervelocity flight, supersonic combustion and detonation, bubble dynamics, and explosive geological events.

Host: AME Department