Select a calendar:
Filter January Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for January
-
CS Colloquium: Hal Daume (University of Maryland) - Learning Language through Interaction
Mon, Jan 13, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Hal Daume, University of Maryland
Talk Title: Learning Language through Interaction
Series: CS Colloquium
Abstract: To have the broadest possible positive impact, machine learning-based natural language processing systems must be able to (a) learn when limited training data exists for the target tasks, languages (and varieties), and domains of interest, and (b) identify and mitigate potential harms in their use, in particular arising from the signals on which they are trained. I will first present new algorithms and applications for learning language processing systems through interaction with people, where implicit and/or explicit user feedback drives learning. I will then discuss learning challenges around "fairness" and how such interactive learning mechanisms can help address them.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Hal Daumé III is a Perotto Chair Professor in Computer Science and Language Science at the University of Maryland, and a Senior Principal Researcher at Microsoft Research. His research focuses on developing learning algorithms for natural language processing, with a focus on interactive learning methods, and techniques for mitigating harms that can arise from automated systems. He earned his Ph.D. from the University of Southern California in 2006, was an inaugural diversity and inclusion co-chair at NeurIPS 2018, is an action editor for TACL, and is program co-chair for ICML 2020.
Host: Fei Sha
Location: Ronald Tutor Hall of Engineering (RTH) - 109
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Colloquium: Marine Carpuat (University of Maryland) - Divergences in Neural Machine Translation
Tue, Jan 14, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Marine Carpuat, University of Maryland
Talk Title: Divergences in Neural Machine Translation
Series: CS Colloquium
Abstract: Despite the explosion of online content worldwide, much information remains isolated by language barriers. While deep neural networks have dramatically improved machine translation (MT), truly breaking language barriers requires not only translating accurately, but also understanding what is said and how it is said across languages. I will first challenge the assumption that translation always preserves meaning, and discuss how to automatically detect when the meaning of a translation diverges from its source. Next, I will show how modeling divergences between MT model hypotheses and reference human translations can improve MT. Finally, I will argue that translation does not necessarily need to preserve all properties of the input and introduce a family of models that let us tailor translation style while preserving input meaning. Taken together, these results illustrate how modeling divergences from common assumptions about translation data can not only improve MT, but also broaden the framing of MT to make it more responsive to user needs.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Marine Carpuat is an Assistant Professor in Computer Science at the University of Maryland. Her research focuses on multilingual natural language processing and machine translation. Before joining the faculty at Maryland, she was a Research Scientist at the National Research Council Canada. She received a PhD in Computer Science and a MPhil in Electrical Engineering from the Hong Kong University of Science & Technology, and a Diplome d'Ingenieur from the French Grande Ecole Supelec. She is the recipient of an NSF CAREER award, research awards from Google and Amazon, best paper awards at *SEM and TALN, and an Outstanding Teaching Award.
Host: Yan Liu
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar
Tue, Jan 14, 2020 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Stefano Ferretti, University of Bologna, Italy
Talk Title: Are Distributed Ledger Technologies Ready for Smart Transportation Systems?
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: In this talk, I'll present a system architecture that exploits Distributed Ledger Technologies (DLTs) and related software technologies to promote the development of smart transportation systems. DLTs provide very interesting features, such as immutability, traceability and verifiability of data. Thus, the designed system architecture allows creating, storing and sharing data generated by vehicles and users through their sensors, while moving. However, some doubts on the scalability and responsiveness of these technologies appear to be well-founded. Experimental results of a real test-bed over IOTA, a promising DLT for IoT, will be discussed.
Biography: Stefano Ferretti is an Associate Professor at the Department of Computer Science and Engineering of the University of Bologna. He received the Laurea degree (summa cum laude) and the Ph.D. in Computer Science from the University of Bologna respectively in 2001 and in 2005. His current research interests include distributed systems, complex networks, data science, fintech and blockchain technologies, multimedia communications, hybrid and distributed simulation. He is in the editorial board of the Simulation Modelling Practice and Theory (SIMPAT) journal, Elsevier, and of the Encyclopedia of Computer Graphics and Games, published by Springer. He is in the technical committee of Computer Communications, Elsevier, as well as Online Social Networks and Media, Elsevier. He acted as editor of special issues on other international journals (i.e., Wiley CPE, Elsevier ComCom). He acted as chairs for several conferences and workshops within flagship conferences, e.g., ACM Mobisys, IEEE InfoCom.
Host: Prof. Bhaskar Krishnamachari, bkrishna@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
ISE 651 - Epstein Seminar
Tue, Jan 14, 2020 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Talk Title: Introduction to Class (No speaker this week)
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Everyone Is Invited
Contact: Grace Owh
-
Mork Family Department of Chemical Engineering and Materials Science Seminar - Lyman L. Handy Colloquia
Tue, Jan 14, 2020 @ 04:00 PM - 05:20 PM
Mork Family Department of Chemical Engineering and Materials Science
Conferences, Lectures, & Seminars
Speaker: Professor Caroline A. Ross, Iron garnets: enabling materials for magnonics, photonics and spintronics
Abstract: Ferromagnetic insulator thin films have emerged as an important component of magnonic, spintronic and magnetooptical devices. Yttrium iron garnet in particular is an excellent insulator with low damping, and has been incorporated into heterostructures that exhibit a plethora of spintronic and magnonic phenomena including spin pumping, spin Seebeck, proximity effects and spin wave propagation. Rare earth (RE) garnet films are both magnetic and magnetoelastic, and their properties can be manipulated by choice of composition and substrate. We grow films of bismuth, thulium, europium, dysprosium and terbium iron garnets with high structural quality down to a thickness of 2.5 nm, about 2 unit cells, and describe the transmission of spin across the interface of garnet/Pt bilayers. Spin orbit torque drives domain wall motion at room temperature at velocities exceeding 4 km/s, and chiral textures and skyrmions are present in garnet films. Iron garnets also exhibit magnetooptical activity and high transparency in the infrared, and we demonstrate integrated magnetooptical isolators comprising Bi and Ce garnets to control the flow of light in photonic integrated circuits.
References: Nature Nanotech. (2019), Optica 6 473 (2019), ACS Photonics 5, 5010 (2018), Phys. Rev. Mater. 2, 094405 (2018), Nature Materials 16, 309-“314 (2017), Adv. Electron. Mater. 3 1600376 (2017), Phys. Rev. B 95 115428 (2017)
Biography: Prof. Ross joined MIT in 1997 and is a Professor in the Department of Materials Science and Engineering. From 1991 to 1997, she was an engineer at Komag Inc, a manufacturer of hard disks. She received her undergraduate degree and Ph.D. in Materials Science and Metallurgy at Cambridge University. She has been chair of the Magnetism and Magnetic Materials Conference and the Materials Research Society Spring Meeting, and has 21 patents awarded and has authored over 400 publications. Prof. Ross is a fellow of the American Physical Society, Institute of Physics (UK), IEEE and Materials Research Society. Her research interests include the magnetic, magnetooptical and multiferroic properties and device applications of thin films, particularly complex oxides such as garnets and perovskites, and the self-assembly of block copolymers and nanocomposite films.
Host: Dr. Armani
Location: John Stauffer Science Lecture Hall (SLH) - 102
Audiences: Everyone Is Invited
Contact: Karen Woo/Mork Family
-
AME Seminar
Wed, Jan 15, 2020 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Jay P. Gore, Purdue
Talk Title: High-Performance Computing Model for Bio-Fuel Combustion with Artificial Intelligence
Abstract: Lean blowout (LBO) calculations and statistical analysis for a conventional (A-2) and an alternative bio-jet fuel (C-1) are performed in a realistic gas turbine combustor geometry. The high-performance computing methodology is developed based on large eddy simulation (LES) models for turbulence and detailed chemistry and flamelet based models for combustion. The bio-jet fuel (C-1) exhibits significantly larger CH2O concentrations in the fuel-rich regions compared to the conventional petroleum fuel (A-2) at an identical equivalence ratio. As expected, the temperature of the recirculating hot gases is an important parameter for maintaining a stable flame. If this temperature falls below a certain threshold value for a given fuel, the evaporation rates and heat release rates decrease significantly and cause lean blowout. This study established the minimum recirculating gas temperature needed to maintain a stable flame for the A-2 and C-1 fuels. Artificial Intelligence (AI) models, based on high fidelity LES data, aimed at early identification of the incipient LBO condition. Sensor-based monitoring using a Support Vector Machine (SVM) detected the onset of LBO approximately 20 ms ahead of the event. A convolutional autoencoder was trained for feature extraction from the mass fraction of the OH for all time-steps resulting in significant dimensionality reduction. The extracted features along with ground truth labels are used to train a support vector machine (SVM) model for binary classification. The binary classification indicated an LBO approximately 30 ms ahead of the actual blowout. This and other early results highlight the promise of AI in much needed engine health monitoring.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Location: James H. Zumberge Hall Of Science (ZHS) - 159
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CS Colloquium: Arjun Guha (University of Massachusetts Amherst) - New Abstractions for New Programming Platforms
Thu, Jan 16, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Arjun Guha, University of Massachusetts Amherst
Talk Title: New Abstractions for New Programming Platforms
Series: CS Colloquium
Abstract: Programmers today have to wrestle with a wide variety of programming platforms. However, traditional programming abstractions and tools were designed for an earlier era, and are often ineffective today, e.g., when building scalable cloud services, reliable robot controllers, and robust web applications. To address these kinds of challenges, we need to rethink the abstractions and tools that programmers employ.
In this talk, we first discuss problems that arise in "serverless computing", which is a new approach to cloud computing. We carefully define an operational semantics for serverless computing, which we then use to 1) formulate correctness criteria, 2) design new modularity mechanisms, and 3) develop a serverless computing accelerator that uses language-based sandboxing and speculative optimizations.
Next, we present fundamental limitations of the web programming model, which affect the design of JavaScript, and make it hard to build robust programming tools that run in web browsers. We address this problem by extending JavaScript with first-class continuations, and efficiently compile the extended language to run in unmodified web browsers.
Finally, we present challenges that arise when debugging robot controllers, and why traditional debugging tools do not help. We present an interactive program repair tool, which uses a MAX-SMT solver to search for corrections to a robot state machine, given a small number of human-provided inputs.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Arjun Guha is an associate professor of Computer Science at the University of Massachusetts Amherst. Using the tools and techniques of programming languages, his research addresses security, reliability, and performance problems in web applications, systems, networking, and robotics. His work has received an ACM SIGPLAN Most Influential Paper Award, an ACM SIGPLAN Distinguished Paper Award, an ACM SIGPLAN Research Highlight, and a Google Faculty Research Award.
Host: Ramesh Govindan
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
NL Seminar Leveraging Context for Natural Language Processing
Thu, Jan 16, 2020 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Samee Ibraheem , UC Berkeley
Talk Title: Leveraging Context for Natural Language Processing
Series: Natural Language Seminar
Abstract: Neural networks have allowed for a host of advances in natural language processing, from text classification to machine translation. However, the effects of contextual information, such as speaker gender or race, on NLP tasks is still an active area of research. In this talk, we first explore how such context can affect an NLP systems accuracy. Next, we investigate methods for incorporating additional context into a machine translation system. Finally, we investigate methods for collecting additional contextual information when the signal is sparse.
Biography: Samee Ibraheem is a PhD student in Computer Science at UC Berkeley working with John DeNero on incorporating context for NLP applications. He received a Bachelors in Neurobiology from Harvard University and is currently supported by an NSF Fellowship.
Host: Emily Sheng
More Info: https://nlg.isi.edu/nl-seminar
Webcast: https://bluejeans.com/s/GDWdF/Location: Information Science Institute (ISI) - Conf Rm 689
WebCast Link: https://bluejeans.com/s/GDWdF/
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: https://nlg.isi.edu/nl-seminar
-
Astani Environmental Engineering Seminar
Fri, Jan 17, 2020 @ 11:00 AM - 12:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Thomas Petersen, Massachusetts Institute of Technology
Talk Title: Continuum Modeling of Reactive Colloids: Transformation of Cement Paste from Sol to Cohesive Gel
Abstract: See attached
Host: Dr. Roger Ghanem
More Information: T. Peterson Abstract.pdf
Location: Ray R. Irani Hall (RRI) - 101
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
CS Colloquium: David Pynadath (USC ICT) - Data-Driven Modeling of Human Social Behavior with Recursive Decision-Theoretic Agents
Tue, Jan 21, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: David Pynadath, USC / ICT
Talk Title: Data-Driven Modeling of Human Social Behavior with Recursive Decision-Theoretic Agents
Abstract: Social scientists, policy makers, and other analysts have increasingly turned to multiagent social simulation as a generative methodology for representing, analyzing, and simulating human behavior. Typical agent-based social simulation methods are attractive, because they use simple, reactive rules that are directly expressible by the people seeking to use them. In contrast, AI provides algorithms for generating autonomous decisions that can match a human level of complexity, but that same complexity is a currently insurmountable obstacle to their use by AI non-experts.
At ICT, we have developed a social simulation framework, PsychSim, using decision-theoretic agents with a theory of mind (ToM) to form mental models about others and use those models to inform their own decision-making. While PsychSim's recursive Partially Observable Markov Decision Processes (POMDPs) offer a generative and transparent approach to social simulation, they share the disadvantage of similarly complex AI languages in that much effort and, often, much error is incurred when building models in them. Fortunately, the growing availability of data about people, their perceptions, and their behaviors offers a novel opportunity for automated support to both reduce the burden and increase the accuracy of the modeling process.
In this talk, I will present algorithms we have developed and applied to two different scenarios: (1) response of an urban population to a disaster, and (2) perceptions of inequality among different national, ethnic, and religious populations. In particular, we analyze the results of applying different automated methods for identifying dynamic influence diagrams whose output matches the beliefs and behaviors that people exhibit in these two scenarios. Because no single model correctly predicted everyone's perceptions and behaviors, we had our algorithm select additional models to capture atypical cases as well. Even with a very restricted space of candidate graphs, our algorithms found multiple models consistent with many of the people in the data sets. We quantify the ambiguity in the models selected by analyzing these cases, and, because of the graphical representation, we can compare models against each other to characterize potential differences in perceptions and behaviors. The result is an automated process that not only generates models for use within multiagent social simulation, but also quantifies the degree of confidence one can place in those models.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. David Pynadath is the Director for Social Simulation Research at USC ICT. He received his Ph.D. from the University of Michigan, Ann Arbor in 1999. He has published papers on multiagent systems, teamwork, social simulation, human-robot interaction, explainable AI, and plan recognition. He is the co-creator and maintainer of PsychSim, the multiagent social simulation framework that was the foundation of the work to be presented. Dr. Pynadath has collaborated with partners in academia and government to apply PsychSim to drive virtual characters in interactive simulations for teaching urban stabilization operations, cross-cultural negotiation, disaster response, and avoiding risky behavior.
Host: Jon May
Location: Ronald Tutor Hall of Engineering (RTH) - 105
Audiences: Everyone Is Invited
Contact: Cherie Carter
-
Astani Civil and Environmental Engineering Seminar
Tue, Jan 21, 2020 @ 02:30 PM - 03:30 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Amr Elnashai, Vice President/Vice Chancellor for Research and Technology Transfer, University of Houston
Talk Title: Machine Learning Approaches in Modeling Complex Structural Problems
Abstract: Please see attached Abstract and a short CV.
Host: Dr. Bora Gencturk
More Information: A. Elnashai Abstract-Short CV.pdf
Location: Kaprielian Hall (KAP) - 209
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
ISE 651 - Epstein Seminar
Tue, Jan 21, 2020 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Güzin Bayraksan, Associate Professor, Ohio State University
Talk Title: A Multistage Distributionally Robust Optimization Approach to Water Allocation under Climate Uncertainty
Host: Prof. Suvrajeet Sen
More Information: January 21, 2020.pdf
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Everyone Is Invited
Contact: Grace Owh
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar
Wed, Jan 22, 2020 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Dimitra Panagou, Aerospace Engineering Department, University of Michigan
Talk Title: Control Synthesis Under Spatiotemporal Specifications
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: Planning and control for multi-agent systems has been a popular topic of research, with applications in numerous real-world autonomous systems. Despite significant progress over the years, challenges such as constraints (in terms of state and time specifications), malicious or faulty information, environmental uncertainty and scalability are still open. In this talk, I will present some of our recent results and ongoing work on a Prescribed-Time Control Barrier Functions framework, where the barriers and underlying controllers meet state and time constraints. The framework builds upon the notions of finite-time and fixed-time stability, and redefines the standard control barrier functions to enable control synthesis that meets spatiotemporal specifications. The efficacy of the approach is illustrated via a spatiotemporal motion planning scenario.
Biography: Dimitra Panagou received the Diploma and PhD degrees in Mechanical Engineering from the National Technical University of Athens, Greece, in 2006 and 2012, respectively. Since September 2014 she has been an Assistant Professor with the Department of Aerospace Engineering, University of Michigan. Prior to joining the University of Michigan, she was a postdoctoral research associate with the Coordinated Science Laboratory, University of Illinois, Urbana-Champaign (2012-2014), a visiting research scholar with the GRASP Lab, University of Pennsylvania (June 2013, fall 2010) and a visiting research scholar with the University of Delaware, Mechanical Engineering Department (spring 2009).
Dr. Panagou's research program emphasizes in the exploration, development, and implementation of control and estimation methods in order to address real-world problems via provably correct solutions. Her research spans the areas of nonlinear systems and control; multi-agent systems and networks; motion and path planning; human-robot interaction; navigation, guidance, and control of aerospace vehicles. She is particularly interested in the development of provably correct methods for the safe and secure (resilient) operation of autonomous systems in complex missions, with applications in robot/sensor networks and multi-vehicle systems (ground, marine, aerial, space). Dr. Panagou is a recipient of a NASA Early Career Faculty Award, of an AFOSR Young Investigator Award, and a Senior Member of the IEEE and the AIAA. More details: http://www-personal.umich.edu/~dpanagou/research/index.html
Host: Paul Bogdan, pbogdan@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
AME Seminar
Wed, Jan 22, 2020 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Roger Ghanem, USC
Talk Title: Probabilistic Learning on Manifolds: The Small Data Challenge
Abstract: As the pace of technological innovation and scientific discovery continues to grow, so does the interest in accelerating their integration. We are thus, increasingly, faced with the task of product development without the benefit of hindsight or historical failures. Examples of this evolving paradigm include new materials and novel configurations of complicated systems with complex behavior. This challenge is exacerbated by the growing interactions between technological and socio-economic systems where failure of a technological component can have implications on social trends and public policy, thus highlighting the need to characterize extreme events both for each component and at the system level. The standard paradigm of mapping knowledge into engineered systems where new systems are essentially construed as perturbations of older systems is not equipped for these emerging requirements. Recent approaches under the general heading of Machine Learning (ML) are motivated by the explosion in sensing technologies. Fundamental advances in these ML methods are being realized at the interface of data science and physics constraints.
In this talk I will describe a recent effort within my group along these ML lines. I will focus on one particular approach, the Probabilistic Learning on Manifolds (PMoL), which is relevant under conditions of small data. This approach aims to augment a (small) training dataset with realizations that share with it some key features making these realizations credible surrogates of the original data. These features consist of 1) co-location on a manifold, and 2) statistical consistency. Thus as a first step, we associated a manifold with the training set, that we believe represents all the fundamental constraints (such as physics). We rely on diffusion maps constructs to delineate the manifold. Construed as fluctuating within this manifold, the training dataset is statistically more significant. As a second step, we generate samples on the manifold that have the same probability distribution as the training set. To this end, we construct a projected Ito equation whose invariant measure is that of the training set, and whose samples are constrained to the manifold.
I will show how the above ideas are used as building blocks in a scramjet optimization problem and the design of a digital twin for a structural composite.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Location: James H. Zumberge Hall Of Science (ZHS) - 159
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CAIS Seminar: Nikos Trichakis (MIT) - Data-driven Methods to Improve Organ Allocation for Transplantation
Wed, Jan 22, 2020 @ 04:15 PM - 05:15 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nikos Trichakis, Massachusetts Institute of Technology
Talk Title: Data-driven Methods to Improve Organ Allocation for Transplantation
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Current organ distribution and allocation policies have resulted in persistent disparities in access to donated organs for transplantation across different waitlisted candidates based on their geographic location, sex, and/or disease. We discuss a novel optimization scheme that leverages machine learning and simulation techniques to devise allocation policies that could alleviate these disparities and allow for a more efficient use of donated organs in the United States. We find that our proposed allocation policies could provide substantial waitlist mortality reduction (of the order of 20% for end-stage liver disease patients), while providing a more equitable organ access in comparison with other proposals.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Nikos Trichakis is an Associate Professor of Operations Management at the MIT Sloan School of Management. His research interests include optimization under uncertainty, data-driven optimization and analytics, with application in healthcare, supply chain management, and finance. Trichakis is also interested in the interplay of fairness and efficiency in resource allocation problems and operations, and the inherent tradeoffs that arise in balancing these objectives.
Host: USC Center for Artificial Intelligence in Society (CAIS)
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Nanyun Peng (USC / ISI) - From Language Understanding to Creative Generation
Thu, Jan 23, 2020 @ 11:00 AM - 12:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Nanyun Peng, USC / ISI
Talk Title: From Language Understanding to Creative Generation
Series: CS Colloquium
Abstract: Recent advances in data-driven approaches have demonstrated appealing results in generating natural languages in applications like machine translation and summarization. However, when the generation tasks are open-ended and the content is under-specified, existing techniques struggle to generate coherent and creative sentences. This happens because the generation models are trained to capture the surface form (i.e. sequences of words), rather than the underlying semantics and discourse structures. Moreover, composing creative pieces such as puns, poems, and stories require deviating from the norm, whereas existing generation approaches seek to mimic the norm and thus are unlikely to lead to truly novel, creative composition. In this talk, I will present several of our recent works related to creative story and pun generation, emphasizing the importance of understanding and control for creative generation.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Nanyun Peng is a Research Assistant Professor of Computer Science at the University of Southern California, and a Research Lead at the Information Sciences Institute. She received a Ph.D. in Computer Science from Johns Hopkins University. Her research focuses on creative language generation, and the robustness and generalizability of natural language understanding, with works being featured in major tech media such as Wired and The Register. Nanyun received a Google Anita Borg Scholarship, a Fred Jelinek Fellowship, and multiple DARPA, IARPA, and NIH grants. She has backgrounds in Linguistics and Economics and held BAs in both.
Host: Xiang Ren
Location: Olin Hall of Engineering (OHE) - 132
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
CS Distinguished Lecture: Manuela Veloso (JP Morgan) - AI for Intelligent Financial Services: Examples and Discussion
Thu, Jan 23, 2020 @ 04:00 PM - 05:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Manuela Veloso, JPMorgan AI Research, on leave: Herbert A. Simon University Professor School of Computer Science, Carnegie Mellon University
Talk Title: AI for Intelligent Financial Services: Examples and Discussion
Series: Computer Science Distinguished Lecture Series
Abstract: After more than 30 years in academia researching in the area of AI, as a student and as a faculty, I joined JPMorgan to create and head an AI research group. In this talk, I will present several concrete examples of the projects we are pursuing in engagement with the lines of business. I will focus on areas related to data, learning from experience, explainability, and ethics. I will conclude with a discussion of my current understanding of the transformational impact that AI can have in the future of financial services.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Manuela M. Veloso is the Head of J.P. Morgan AI Research, which pursues fundamental research in areas of core relevance to financial services, including data mining and cryptography, machine learning, explainability, and human-AI interaction. J.P. Morgan AI Research partners with applied data analytics teams across the firm as well as with leading academic institutions globally.
Professor Veloso is on leave from Carnegie Mellon University as the Herbert A. Simon University Professor in the School of Computer Science, and the past Head of the Machine Learning Department. With her students, she had led research in AI, with a focus on robotics and machine learning, having concretely researched and developed a variety of autonomous robots, including teams of soccer robots, and mobile service robots. Her robot soccer teams have been RoboCup world champions several times, and the CoBot mobile robots have autonomously navigated for more than 1,000km in university buildings.
Professor Veloso is the Past President of AAAI, (the Association for the Advancement of Artificial Intelligence), and the co-founder, Trustee, and Past President of RoboCup. Professor Veloso has been recognized with a multiple honors, including being a Fellow of the ACM, IEEE, AAAS, and AAAI. She is the recipient of several best paper awards, the Einstein Chair of the Chinese Academy of Science, the ACM/SIGART Autonomous Agents Research Award, an NSF Career Award, and the Allen Newell Medal for Excellence in Research.
Professor Veloso earned a Bachelor and Master of Science degrees in Electrical and Computer Engineering from Instituto Superior Tecnico in Lisbon, Portugal, a Master of Arts in Computer Science from Boston University, and Master of Science and PhD in Computer Science from Carnegie Mellon University. See www.cs.cmu.edu/~mmv/Veloso.html for her scientific publications.
Host: Maja Mataric and Heather Culbertson
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Munushian Lecture - Raymond Beausoleil, Friday, January 24th at 2pm in EEB 132
Fri, Jan 24, 2020 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Raymond G. Beausoleil, Hewlett Packard Labs, Palo Alto, CA
Talk Title: Large-Scale Integrated Photonics for Accelerated Communication and Computing
Abstract: The massive explosion in data acquisition, processing, and archiving, hindered by the end of Moore's Law, creates an opportunity for a complete redesign of the information technology stack, including hardware system architectures,
devices, networks, and software to enable future computing systems with multi-exascale performance-”and beyond. Key
to success in this challenging endeavor will be the paradigm shift of moving from a processor-centric to a memory-centric
approach. Architectural changes are necessary to overcome the limitations of the traditional compute-centric model, and will
require new network layouts (e.g., Hyper-X) and new high-performance memory-addressing protocols (e.g., Gen-Z) that rely on a high-bandwidth and energy-efficient photonic interconnect. We will describe the state-of-the-art in datacom photonics and present the advances that will be necessary-”and are already appearing in R&D laboratories-”to enable memory-centric computing at scale.
Memory-centric computing would be an ideal heterogeneous platform for in-memory hardware accelerators that can be
brought to bear on specific problems of scientific, engineering, or industrial interest. Ideally, a mature software ecosystem would simplify the design of a plug-and-play network interface that would allow users to compare the performance of the most advanced accelerators. We will describe such an accelerator-”a coherent optical Ising machine-”that targets NP-hard problems that scale exponentially as a function of system size and are common to applications such as traffic flow optimization, supply chain management, airline scheduling, and DNA sequencing. Optical Ising machines based on symmetry-breaking in pulsed optical parametric oscillators have already been shown to outperform a commercially-available quantum annealer, and there is good reason to believe that integrated photonic implementations of this approach can achieve similar results.
Biography: Ray Beausoleil is a Hewlett Packard Enterprise (HPE) Senior Fellow and a Senior Vice President, and an Adjunct Professor of Applied Physics at Stanford University. At HPE, he leads the Large-Scale Integrated Photonics research group, and is responsible for research on the applications of optics at the micro/nanoscale to high-performance classical and quantum information processing. His current projects include photonic interconnects for exascale computing, and low-power complex nanophotonic circuits. Ray received the Bachelor of Science with Honors in Physics from the California Institute of Technology in 1980, and his Ph.D. in Physics from Stanford in 1986 as a member of Ted Hänsch's research group. In 1996, Ray became a member of the technical staff at HP Laboratories. Among his early accomplishments at HP, he invented the optical paper-navigation algorithms incorporated into the HP/Agilent optical mouse, and now HP's large-format printers. He has published over 300 papers and conference proceedings and five
book chapters. He has over 150 patents issued, and over three dozen pending. He is a Fellow of both the American Physical Society and the Optical Society of America, and the recipient of the 2016 APS Distinguished Lectureship on the Applications of Physics.
Host: ECE-Electrophysics
More Info: https://minghsiehee.usc.edu/about/lectures/munushian/
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Marilyn Poplawski
Event Link: https://minghsiehee.usc.edu/about/lectures/munushian/
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute Seminar
Mon, Jan 27, 2020 @ 03:30 PM - 04:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Mihai Udrescu, Department of Computer & Information Technology at the Politehnica University of Timisoara (UPT), Romania
Talk Title: From Quantum Computing to Complex Networks: Addressing Tough Questions in Biological and Social Systems
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: There is a fundamental difference between a technological and a natural system. While the former is the product of an intelligent designer, the latter is the result of an emerging process where randomness, volatility, and environment aggression play an important role. This talk will approach several hard problems in natural systems with computer-based complex network analysis, from drug repurposing and patient phenotype identification to specific patterns of opinion spreading in social networks. The talk will also cast light on the presenter's academic journey, from quantum computing to network science.
Biography: Mihai Udrescu is a Professor with the Department of Computer and Information Technology at the Politehnica University of Timisoara (UPT), Romania, and a Fulbright Visiting Scholar at the Electrical and Computer Engineering Department, Carnegie Mellon University (September 2019 - February 2020). He received his Ph.D. in Computer Engineering from UPT in 2005. Mihai Udrescu's research is targeting the physics of computation and the design of emerging computer systems such as quantum circuits and bio-inspired hardware. Recently, he got involved in research projects that focus on network science, online social networks, and network medicine.
Host: Paul Bogdan, pbogdan@usc.edu
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
ISE 651 - Epstein Seminar
Tue, Jan 28, 2020 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Joe Qin, Fluor Professor, Fellow of IFAC, IEEE, and AIChE
Talk Title: DYNAMIC LATENT VARIABLE ANALYTICS FOR ANOMALY MONITORING OF MANUFACTURING PROCESS DATA
Host: Prof. Jong-Shi Pang
More Information: January 28, 2020.pdf
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Everyone Is Invited
Contact: Grace Owh
-
Astani Civil and Environmental Engineering Seminar
Wed, Jan 29, 2020 @ 03:00 PM - 04:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Casey Chosewood, Director of Total Worker Health, NIOSH, CDC
Talk Title: Help... I Think My Job Is Killing Me: New Solutions for the Risks of Modern Work
Abstract: See attached abstract and bio.
Host: Dr. Burcin Becerik- Gerber
More Information: C. Chosewood Abstract 01-29-2020.pdf
Location: Ray R. Irani Hall (RRI) - 101
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
AME Seminar
Wed, Jan 29, 2020 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Chris Roh, Caltech
Talk Title: Hydrofoiling Honeybee
Abstract: Honeybees display a unique bio-locomotion strategy at the air-water interface. When waters adhesive force traps them on the surface, their wetted wings lose ability to generate aerodynamic thrust. However, they adequately locomote, reaching a speed up to three body lengths-1. Honeybees use their wetted wings as hydrofoils for their water surface propulsion. Their locomotion imparts hydrodynamic momentum to the surrounding water in the form of asymmetric waves and a deeper water jet stream, generating approximately 20 μN average thrust. The wing kinematics show that the wings stroke plane is skewed, and the wing supinates and pronates during its power and recovery strokes, respectively. The flow under a mechanical model wing mimicking the motion of a bees wing further shows that non-zero net horizontal momentum is imparted to the water, demonstrating net thrust. Moreover, a periodic acceleration and deceleration of water is observed, which provides additional forward movement by recoil locomotion. Scaling analysis of the hydrodynamic forces associated with the wing motion indicates that the wings utilize added mass force (unsteady inertial force associated with the pulling of the water attached to the wing). Hydrofoiling highlights the versatility of their flapping-wing systems that are capable of generating propulsion with fluids whose densities span three orders of magnitude. This discovery inspires a novel aerial-aquatic hybrid vehicle.
Host: AME Department
More Info: https://ame.usc.edu/seminars/
Location: James H. Zumberge Hall Of Science (ZHS) - 159
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
NL Seminar-BlackBox NLP: What are we looking for, and where do we stand?
Thu, Jan 30, 2020 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Sarah Wiegreffe , Georgia Tech
Talk Title: BlackBox NLP: What are we looking for, and where do we stand?
Series: Natural Language Seminar
Abstract: The widespread adoption of deep learning in NLP has led to a new state-of-the-art on many tasks. Neural nets are complex systems that are hard to interpret, leaving researchers with little ability to say *why* their model is doing so well. As a consequence, interpretability and explainability hold a new relevance. In this talk, I will present case studies in the subfield of interpretability for NLP, as well as the research goals of the subtopics that fall under this umbrella. I will present a case-study of the necessary conditions for attention modules to be used for explaining classification model predictions, as well as a clinical application of attention mechanisms in physician decision support. I will conclude by discussing future directions, including in natural language explanations for reinforcement learning systems.
Biography: Sarah Wiegreffe is a Computer Science PhD student in the School of Interactive Computing at Georgia Tech. Her research lies at the intersection of machine learning and NLP, with a particular interest in interpretability, explainability, and model robustness. In the past, she has worked in clinical applications of NLP and ML. During her PhD, she has held research internships at Google AI and Sutter Health. She obtained her B.S. in Data Science from the College of Charleston. In her free time, Sarah enjoys rock climbing, traveling, and rock music.
Host: Emily Sheng
More Info: https://nlg.isi.edu/nl-seminar
Webcast: https://bluejeans.com/s/NqZd0Location: Information Science Institute (ISI) - CR #1014
WebCast Link: https://bluejeans.com/s/NqZd0
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: https://nlg.isi.edu/nl-seminar
-
Sonny Astani Civil and Environmental Engineering Seminar
Thu, Jan 30, 2020 @ 04:00 PM - 05:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Prof. Krista Wigginton, Ph.D., University of Michigan
Talk Title: Recent Advancements in Environmental Virus Fate and Detection
Abstract: Recent Advancements in Environmental Virus Fate and Detection
The detection and removal of infectious viruses in the environment is critical for protecting human health. A number of factors complicate virus detection and obscure their environmental fate,including their small size, their lack of conserved genes, their rapid evolution, and the difficulty in
culturing many important strains. This seminar will review recent advances in environmental virology, including our work on the mechanistic fate and detection of viruses in wastewater and
drinking water treatment processes.
Biography: Dr. Krista Rule Wigginton is an associate professor of Civil and Environmental Engineering at the
University of Michigan. Prior to joining the faculty at UM, she was an assistant professor at the University of Maryland, College Park from 2011-2012. Her research focuses on applications of environmental biotechnology in drinking water and wastewater treatment. In particular, her research group develops new methods to detect and analyze the fate of emerging pollutants inthe environment.
Dr. Wigginton received her B.S. degree in Chemistry from the University of Idaho, and her M.S. and Ph.D. degrees in Environmental Engineering from Virginia Tech. After
completing her Ph.D. degree, she worked as a postdoctoral researcher at Ãcole Polytechnique Fédérale de Lausanne (EPFL) in Switzerland from 2008-2011.
Host: Dr. Daniel McCurry
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
AI for Software and Software for AI
Fri, Jan 31, 2020 @ 10:00 AM - 11:30 AM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Lin Tan, Purdue University
Talk Title: AI for Software and Software for AI
Abstract: This talk will present research focuses in two directions: (1) using software testing approaches to improve the dependability of machine learning systems, and (2) leveraging machine learning and natural language processing techniques to improve software dependability. Machine learning software is widely used in domains including aircraft collision avoidance systems, Alzheimers disease diagnosis, and autonomous driving cars. Despite the requirement for high reliability, machine learning software is difficult to test and debug. This talk will describe CRADLE, a new approach that (1) performs cross-implementation inconsistency checking to detect bugs in deep learning software, and (2) analyzes anomaly propagation to localize faulty functions in deep learning software. On the other hand, machine learning and natural language processing techniques have unique advantages in completing and automating challenging software development tasks. This talk will present techniques that automatically analyze software text, such as code comments, API documentation, and processor specifications, to extract specifications, generate test cases, and detect software bugs. In addition, this talk will discuss how to build machine learning models to produce specifications and bug patterns automatically from existing bugs and their commit messages to find new bugs.
Biography: Lin Tan is an Associate Professor of Computer Science at Purdue University. She received her PhD from the University of Illinois, Urbana-Champaign. Her research interests include software dependability and software text analytics. Dr. Tan co-authored papers have received ACM SIGSOFT Distinguished Paper Awards at MSR in 2018 and FSE in 2016; and IEEE Micros Top Picks in 2006. Dr. Tan was a recipient of Canada Research Chair, an NSERC Discovery Accelerator Supplements Award, an Ontario Early Researcher Award, an Ontario Professional Engineers Award -” Engineering Medal for Young Engineer, two Google Faculty Research Awards, a Facebook research award, and an IBM CAS Research Project of the Year Award.
Host: Xuehai Qian, xuehai.qian@usc.edu
More Information: 200131_Lin Tan_CENG.pdf
Location: Ronald Tutor Hall of Engineering (RTH) - 526
Audiences: Everyone Is Invited
Contact: Brienne Moore
