Select a calendar:
Filter November Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Conferences, Lectures, & Seminars
Events for November
-
NL Seminar-Exposing Brittleness in Reading Comprehension Systems
Thu, Nov 01, 2018 @ 11:00 AM - 12:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Robin Jia, Stanford University
Talk Title: Exposing Brittleness in Reading Comprehension Systems
Series: Natural Language Seminar
Abstract: Reading comprehension systems that answer questions over a context passage can often achieve high test accuracy, but they are frustratingly brittle: they often rely heavily on superficial cues, and therefore struggle on out-of-domain inputs. In this talk, I will describe our work on understanding and challenging these systems. First, I will show how to craft adversarial reading comprehension examples by adding irrelevant distracting text to the context passage. Next, I will present the newest version of the SQuAD dataset, SQuAD 2.0, which tests whether models can distinguish answerable questions from similar but unanswerable ones. Finally, I will share some observations from our recent attempts to use reading comprehension systems as a natural language interface for building other NLP systems.
Biography: Robin Jia is a fifth-year PhD student advised by Percy Liang at Stanford University. He is an NSF Graduate Fellow, and has received Outstanding Paper and Best Short Paper Awards from EMNLP and ACL, respectively.
Host: Xusen Yin
More Info: http://nlg.isi.edu/nl-seminar/
Location: Information Science Institute (ISI) - 6th Floor Conf Rm-CR# 689
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
-
CS Distinguished Lecture: Cynthia Dwork (Harvard University) - Skewed or Rescued? The Emerging Theory of Algorithmic Fairness
Thu, Nov 01, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Cynthia Dwork, Harvard University
Talk Title: Skewed or Rescued? The Emerging Theory of Algorithmic Fairness
Series: Computer Science Distinguished Lecture Series
Abstract: Data, algorithms, and systems have biases embedded within them reflecting designers' explicit and implicit choices, historical biases, and societal priorities. They form, literally and inexorably, a codification of values. 'Unfairness' of algorithms - for tasks ranging from advertising to recidivism prediction - has attracted considerable attention in the popular press. The talk will discuss recent work in the nascent mathematically rigorous study of fairness in classification and scoring.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Cynthia Dwork, the Gordon McKay Professor of Computer Science at the John A. Paulson School of Engineering and Applied Sciences at Harvard, the Radcliffe Alumnae Professor at the Radcliffe Institute for Advanced Study, and an Affiliated Faculty Member at Harvard Law School, is renowned for placing privacy-preserving data analysis on a mathematically rigorous foundation. With seminal contributions in cryptography, distributed computing, and ensuring statistical validity, her most recent focus is on fairness in classification algorithms. Dwork is a member of the US National Academy of Sciences, the US National Academy of Engineering, and the American Philosophical Society, and is a Fellow of the American Academy of Arts and Sciences and of the ACM.
Host: Computer Science Department
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Sample Complexity of Partition Identification using Multi-armed Bandits with Applications to Nested Monte Carlo
Fri, Nov 02, 2018 @ 02:00 AM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Prof. Sandeep Juneja, TIFR, Mumbai, India
Talk Title: Sample Complexity of Partition Identification using multi-armed Bandits with Applications to Nested Monte Carlo
Series: Special/Joint CPS/CommNetS Seminar
Abstract: Given a vector of probability distributions, or arms, each of which can be sampled independently, we consider the problem of identifying the partition to which this vector belongs from a finitely partitioned universe of such vector of distributions. We study this as a pure exploration problem in multi-armed bandit settings and develop sample complexity bounds on the total mean number of samples required for identifying the correct partition with high probability. This framework subsumes well-studied problems in the literature such as finding the best arm or the best few arms. We consider distributions belonging to the single parameter exponential family and primarily consider partitions where the vector of means of arms lie either in a given set or its complement. The sets considered correspond to distributions where there exists a mean above a specified threshold, where the set is a half space and where either the set or its complement is convex. In all these settings, we characterize the lower bounds on mean number of samples for each arm. Further, we propose algorithms that can match these bounds asymptotically with decreasing probability of error. Applications of this framework may be diverse. We briefly discuss a few associated with nested Monte Carlo and its applications to finance.
Biography: Sandeep is a Professor and Dean at the School of Technology and Computer Science in Tata Institute of Fundamental Research in Mumbai. His research interests lie in applied probability including in mathematical finance, Monte Carlo methods, multi-armed bandit based sequential decision making, and game theoretic analysis of queues. He is currently on the editorial board of Stochastic Systems. Earlier he has been on editorial boards of Mathematics of Operations Research, Management Science and ACM TOMACS.
Host: Rahul Jain
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Talyia White
-
W.V.T. RUSCH ENGINEERING HONORS COLLOQUIUM
Fri, Nov 02, 2018 @ 01:00 PM - 01:50 PM
USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Speaker: Prof. Aaron D. Ames, California Institute of Technology, Dept. of Mechanical and Civil Engineering
Talk Title: Towards the Robots of Science Fiction
Host: EHP and Dr. Prata
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Amanda McCraven
-
Astani Civil and Environmental Engineering Seminar
Fri, Nov 02, 2018 @ 03:00 PM - 04:00 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Damian Helbling, Ph.D., Cornell University
Talk Title: Organic chemical contaminants in the aquatic environment: new tools for characterization and remediation of impacted environments
Abstract: See attached
Host: Dr. Daniel McCurry
More Information: Helbling_Announcement.docx
Location: Ray R. Irani Hall (RRI) - 101
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
Essentials of Composites ManufacturingSat, Nov 03, 2018 @ 08:00 AM - 05:00 PM
Executive Education
Conferences, Lectures, & Seminars
Abstract: Essentials of Composites Manufacturing provides a high-level overview of manufacturing science and engineering for aerospace composite structures, focusing on prepreg and liquid molding processes, including hands-on laboratory demonstrations.
Course participants will complete a multiple-choice quiz as a knowledge assessment, available online at the end of the course. When the course and quiz have been successfully completed, participants will receive USC Continuing Education Units.
More Info: https://viterbiexeced.usc.edu/engineering-program-areas/chemical-engineering-materials-science/essentials-composites-manufacturing/
Audiences: Registered Attendees
Contact: Corporate & Professional Programs
-
Seminars in Biomedical Engineering
Mon, Nov 05, 2018 @ 12:30 PM - 01:50 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Robert Wodnicki, USC Biomedical Engineering, PhD Student
Talk Title: IC design for Ultrasound
Host: Qifa Zhou
Location: Olin Hall of Engineering (OHE) - 122
Audiences: Everyone Is Invited
Contact: Mischalgrace Diasanta
-
Fall 2018 Joint CSC@USC/CommNetS-MHI Seminar Series
Mon, Nov 05, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Sonja Glavaski, ARPA-E
Talk Title: Building Efficient, Sustainable and Resilient Grid by Controlling the Edge
Abstract: The evolution of the electricity grid faces significant challenges if it is to integrate and accept more energy from renewable generation and other Distributed Energy Resources (DERs). To maintain grid's reliability and turn intermittent power sources into major contributors to the U.S. energy mix, we have to think about the grid differently and design it to be smarter and more flexible. ARPA-E is interested in disruptive technologies that enable increased integration of DERs by real-time adaptation while maintaining grid reliability and reducing cost for customers with smart technologies. This talk will identify opportunities in developing next generation control technologies and grid operation paradigms that address these challenges and enable efficient, sustainable and reliable transmission and distribution of electrical power. Summary of ARPA-E NODES (Network Optimized Distributed Energy Systems) Program funding development of these technologies will be presented. Innovative approaches to coordinated management of bulk generation, DERs, flexible loads, and storage assets with multiple roles, and revenue streams will be discussed.
Biography: Dr. Sonja Glavaski is a Program Director at the Advanced Research Projects Agency-Energy (ARPA-E) overseeing diverse project portfolio developing innovative and disruptive technologies that would facilitate cost-effective building energy audits, more efficient power generation, electrification of transportation, and enable electricity grid to be more flexible and resilient. Her technical focus area is data analytics, and distributed control of complex, cyber-physical systems with emphasis on operations and security of energy systems. Dr. Sonja Glavaski worked on establishment of several grid modernization and transportation focused ARPA-E programs. She spearheaded development and is currently helming ARPA-E NODES Program that aims to develop transformational grid management and control methods to create a virtual energy storage system based on use of flexible loads and distributed energy resources (DERs). Prior to joining ARPA-E, Dr. Glavaski served as a Control Systems Group Leader at United Technologies Research Center (UTRC), where she led a team of multi-disciplinary scientists working on developing game changing technologies for energy efficient building HVAC/R systems, wind turbines, fuel cells and flow batteries. It was at UTRC that she recognized the need to develop more systematic ways to integrate and operate all of these technologies with the electricity grid. Before being at UTRC, Dr. Glavaski led key programs at Eaton Innovation Center and Honeywell Labs. During her 20-plus-year career, Dr. Glavaski has contributed significantly to technical advancements in numerous product areas, including energy systems, vehicles and aircraft systems. Dr. Glavaski received PhD and MS in Electrical Engineering from California Institute of Technology, and Dipl. Ing and MS in Electrical Engineering from the University of Belgrade.
Host: Mihailo Jovanovic, mihailo@usc.edu
More Info: http://csc.usc.edu/seminars/2018Fall/glavaski.html
More Information: 18.11.05_Glavaski_ARPA-E Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
Event Link: http://csc.usc.edu/seminars/2018Fall/glavaski.html
-
**No Epstein Seminar, ISE 651 This Week (Due to INFORMS)**
Tue, Nov 06, 2018
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Audiences: Everyone Is Invited
Contact: Grace Owh
-
RASC Seminar: Sanjiv Singh (CMU) - Flying Cars: What's taking so long?
Tue, Nov 06, 2018 @ 10:00 AM - 11:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Sanjiv Singh, CMU
Talk Title: Flying Cars: What's taking so long?
Series: RASC Seminar Series
Abstract: Almost a hundred years ago, before we had foreseen a world where cars drive themselves in traffic, the idea of a vehicle that could be both driven and flown had already taken hold of the public imagination. However compelling the imagery facilitated by the media and science fiction, we are still not close to an aerial analog of the self-driving car. While commonplace flying cars might be some time in coming, we might still ask what would be possible if we could realize "personal aviation". We could ask how such vehicles could operate safely and what steps we need to take to hasten their feasibility.
Because flying cars would almost certainly have to be autonomous to be operable by non-pilots, many of the
building blocks needed have immediate relevance in the agenda for developing autonomous drones, as well as,
safety aids for pilots of the large number of aircraft that must fly at low elevation and land at unprepared sites.
In my talk, I will discuss results from recent work with autonomous aircraft operating in unstructured environments
focused on four technical goals: fly safe, land safe, fly without GPS, and, even when critical systems fail. I will
show how presence of a human onboard an autonomous flying vehicle can improve both performance and reliability.
I also will show results from a new class of methods that simultaneously produce dense reconstruction and
low-drift 6DOF pose estimation in real time, with application to various scales of aircraft.
Biography: Sanjiv Singh is a Research Professor at the Robotics Institute, Carnegie Mellon University and the CEO of
Near Earth Autonomy. He started his career working on the earliest autonomous ground vehicles to operate
outdoors in 1985. Since then, he has led research efforts with applications in aviation, agriculture, mining and
construction. In 2010 he led a team that demonstrated the first autonomous, full-scale helicopter capable of
take off, search for viable landing sites and safe descent. He holds a Ph.D. in Robotics from Carnegie Mellon
University and is the founding editor of the Journal of Field Robotics.
Host: Gaurav Sukhatme
Location: Ronald Tutor Hall of Engineering (RTH) - 406
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Mork Family Department of Chemical Engineering and Materials Science Seminar - Distinguished Lecture Series
Tue, Nov 06, 2018 @ 04:00 PM - 05:20 PM
Mork Family Department of Chemical Engineering and Materials Science
Conferences, Lectures, & Seminars
Speaker: Professor Paul Salvador, Department of Materials Science and Engineering, Carnegie Mellon University
Talk Title: Combinatorial Substrate Epitaxy and the Design of Materials
Abstract: Over the past few decades, advancement in epitaxial growth of complex oxides has been remarkable. Most of these advances have been made using a surprisingly small number of commercially available single crystal substrates (perovskite, fluorite, corundum, rock salt, etc.). If appropriate substrates were available across all structural families, we would accelerate the design and synthesis of new materials with attractive properties. I will discuss our work on an approach to solving this dilemma, called Combinatorial Substrate Epitaxy (or CSE). In CSE we use epi-polished polycrystalline ceramics as substrates and automated electron backscatter diffraction as a non-destructive local structural characterization method. We map the orientation of hundreds of substrate grains prior to growth, then map film orientations on those same grains after deposition and use in-house programs to determine the epitaxial orientation relationships (ORs) across all of orientation space (in a single experiment). Importantly, each grain in a polycrystal behaves as an individual single crystal substrate, usually exhibiting grain-over-grain epitaxial growth. A bit surprisingly, there are only a small number (one or two) of epitaxial ORs observed across orientation space, which are largely independent of the surface orientation. On substrates where competitive polymorph nucleation occurs, the winner of the competition can be rationalized using observed ORs and planar matching on low-index orientations. Because of this, we have been able to develop a computational method that guides epitaxial synthesis. Density functional theory computations are combined with continuum models of nucleation to guide the selection of thermodynamically accessible materials and polymorph directing substrates. I will use a variety of film / substrate structural pairs to make these points, including BO2, B2O3, ABO3, A2BO4, and A2B2O7. I will describe how CSE opens the door for the predictive design of materials with new properties and the synthesis pathways to make them.
Host: Dr. Jayakanth Ravichandran
Location: 200
Audiences: Everyone Is Invited
Contact: Karen Woo/Mork Family
-
Why Blocks and Why Chains; A First Principles (Re)Design of Blockchains
Wed, Nov 07, 2018 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Pramod Viswanath, Co-Founder and CEO, Applied Protocol Research, Inc University of Illinois at Urbana-Champaign
Talk Title: Why Blocks and Why Chains; A First Principles (Re)Design of Blockchains
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: Today's blockchains do not scale in a meaningful way. As more nodes join the system, the efficiency of the system (computation, communication, and storage) degrades, or at best stays constant. Furthermore, the security of the permissionless system imposes limitations on the core performance metrics of throughput, latency and confirmation probability. We take a first principle approach to the blockchain ecosystem addressing each of the various components holistically. Our approach is characterized by seeking fundamental limits (those prescribed by the physics of the underlying network) to performance and designing algorithms that attain them. This research is informed by decades of experience in information theory, coding theory, algorithms, wireless communication and, packet networks. This talk will highlight key outcomes of this research program, including Prism (a new consensus algorithm that guarantees information theoretically optimal throughput, latency, reliability), Spider (a new networking protocol for off-chain payment channels), Polyshard (a new coded storage architecture), and Dandelion (a new network privacy layer).
https://arxiv.org/abs/1810.08092;
https://arxiv.org/abs/1809.10361;
https://arxiv.org/abs/1809.05088;
https://arxiv.org/abs/1809.07468;
Biography: Pramod Viswanath received the Ph.D. degree in EECS from UC Berkeley in 2000. From 2000 to 2001, he was a member of research staff at Flarion technologies, NJ. Since 2001, he is on the faculty at University of Illinois at Urbana Champaign in Electrical and Computer Engineering, where he currently is a professor. He is a coauthor, with David Tse, of the text Fundamentals of Wireless Communication, which has been used in over 60 institutions around the world. He is coinventor of the opportunistic beamforming method and codesigner of Flash-OFDM communication algorithms adapted into fourth-generation cellular systems.
His current research interests are in blockchain technologies from a variety of angles: networking protocols, consensus algorithms, payment channels, distributed coded storage and incentive designs. He is co-founder and CEO of Applied Protocol Research, a startup doing research on blockchain technologies. Applied Protocol Research is staffed by academics (professors, PhDs, and intern graduate students), with a wide variety of backgrounds (EE/CS/ECON covering both theory/systems) from different institutions (Berkeley, CMU, Illinois, MIT, Stanford, USC, UW-Seattle). This talk is joint work by the speaker with: Mohammad Alizadeh (MIT), Salman Avestimehr (USC), Giulia Fanti (CMU), Sreeram Kannan (UW-Seattle), Sewoong Oh (Illinois) and David Tse (Stanford).
Host: Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - EEB 248
Audiences: Everyone Is Invited
Contact: Talyia White
-
Astani Civil and Environmental Engineering Seminar
Wed, Nov 07, 2018 @ 11:30 AM - 12:30 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Jesse Kroll, Ph.D., Massachusetts Institute of Technology
Talk Title: Low-cost air quality sensors for measuring atmospheric
Abstract: See attachment
Host: Dr. Patrick Lynett and Dr. George Ban-Weiss
More Information: Jesse_Kroll_Announcement_v2.pdf
Location: Ray R. Irani Hall (RRI) - 101
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
CAIS Seminar: Dr. Adnan Darwiche (UCLA) - Explaining and Verifying AI Systems
Wed, Nov 07, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Adnan Darwiche, UCLA
Talk Title: Explaining and Verifying AI Systems
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Explaining the decisions of AI systems and formally verifying their properties have come into focus recently. In this talk, Dr. Darwiche will discuss an approach for explaining and verifying Bayesian network classifiers, which is based on compiling them into equivalent and symbolic decision graphs. He will also discuss a new class of circuits that are as expressive as neural networks and that can be synthesized from Bayesian network models, allowing one to provide formal guarantees on their behaviors regardless of how they are trained from data.
This lecture satisfies requirements for CSCI 591: Research Colloquium
Biography: Dr. Adnan Darwiche is a professor and chairman of the computer science department at UCLA. He directs the automated reasoning group which focuses on probabilistic and logical reasoning, and their applications including to machine learning (http://reasoning.cs.ucla.edu/.
Host: Milind Tambe
Location: Mark Taper Hall Of Humanities (THH) - 301
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Paul Rosenbloom (USC) - A Common Model of Cognition (née A Standard Model of the Mind)
Wed, Nov 07, 2018 @ 06:00 PM - 07:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Paul Rosenbloom , USC
Talk Title: A Common Model of Cognition (née A Standard Model of the Mind)
Series: Computer Science Colloquium
Abstract: A common (or standard) model captures a community consensus over a coherent region of science, serving as a cumulative reference point for the field that can provide guidance for both research and applications, while also focusing efforts to extend or revise it. An effort has been initiated recently to build such a model for human-like minds, computational entities -" whether natural or artificial -" whose structures and processes are substantially similar to those found in human cognition. The core hypothesis is that cognitive architectures provide the appropriate computational abstraction for defining such a model, although the model is not itself such an architecture. The model began as a consensus at the 2013 AAAI Fall Symposium on Integrated Cognition but has since been extended via a synthesis across three existing cognitive architectures: ACT-R, Sigma, and Soar. The resulting model spans key aspects of structure and processing, memory and content, learning, and perception and motor; highlighting loci of architectural agreement as well as disagreement with the consensus while identifying potential areas of remaining incompleteness. Work to build this into a community-wide effort is also in progress.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Paul Rosenbloom is Professor of Computer Science in the Viterbi School of Engineering at the University of Southern California and Director for Cognitive Architecture Research at USC's Institute for Creative Technologies. He was a member of USC's Information Sciences Institute for two decades, ending as its Deputy Director, and earlier was on the faculty at Carnegie Mellon University and Stanford University. His research concentrates on cognitive architectures (integrated models of the fixed structures underlying minds), the possibility of a Common Model of Cognition (a community consensus concerning what must be in a cognitive architecture), and on the nature and structure of computing as a scientific domain and its overlap with the other domains of human study. He is a Fellow of the Association for the Advancement of Artificial Intelligence, the Association for the Advancement of Science, and the Cognitive Science Society.
More Info: https://goo.gl/forms/w7WRcpF7xqY3As4T2
Host: AAAI@USC
Location: Mark Taper Hall Of Humanities (THH) - 202
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
MASCLE Machine Learning Seminar: Quanquan Gu (UCLA) - New Variance Reduction Algorithms for Nonconvex Finite-Sum Optimization
Thu, Nov 08, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Quanquan Gu, UCLA
Talk Title: New Variance Reduction Algorithms for Nonconvex Finite-Sum Optimization
Series: Machine Learning Seminar Series
Abstract: Nonconvex finite-sum optimization problems are ubiquitous in machine learning such as training deep neural networks. To solve this class of problems, various variance reduction based stochastic optimization algorithms have been proposed, which are guaranteed to converge to stationary points and enjoy improved gradient complexity than vanilla stochastic gradient descent. An natural question is whether there is still space for improvement to further speed up the finding of first-order stationary points and even local minimas.
In the first part of this talk, I will introduce our work for finding first-order stationary points in nonconvex finite-sum optimization that further pushes the frontiers of this line of research. In particular, I will introduce a new stochastic nested variance reduced gradient algorithm (SNVRG) that achieves the fastest convergence rate to first-order stationary points in the literature by reducing the variance in stochastic algorithms through multiple referencing points and gradients. It outperforms the folklore variance reduction methods such as stochastic variance reduced gradient (SVRG) and stochastically controlled stochastic gradient (SCSG).
In the second part of the talk, I will talk about methods for finding second-order stationary points (i.e., local minima) in nonconvex finite-sum optimization. Specifically, I will introduce a stochastic variance reduced cubic regularization algorithm that achieves the state-of-the-art second-order oracle complexity for finding local minima in nonconvex optimization.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Host: Yan Liu, USC Machine Learning Center
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
13th Annual Mork Family Department Student Symposium
Fri, Nov 09, 2018
Mork Family Department of Chemical Engineering and Materials Science
Conferences, Lectures, & Seminars
Location: Edward L. Doheny Jr. Memorial Library (DML) - 240
Audiences: Everyone Is Invited
Contact: Karen Woo/Mork Family
-
W.V.T. RUSCH ENGINEERING HONORS COLLOQUIUM
Fri, Nov 09, 2018 @ 01:00 PM - 01:50 PM
USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Yanghee Woo and Dr. Lily Lai, Associate Clinical Professors of Surgery, City of Hope
Talk Title: Technical Medicine: The Future of Surgical Robotics
Host: EHP and Dr. Prata
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Amanda McCraven
-
NL Seminar-Taming the scientific literature: progress and challenges
Fri, Nov 09, 2018 @ 03:00 PM - 04:00 PM
Information Sciences Institute
Conferences, Lectures, & Seminars
Speaker: Waleed Ammar, AI2-Allen Inst.
Talk Title: Taming the scientific literature: progress and challenges
Series: Natural Language Seminar
Abstract: The magnitude and growth of the scientific literature can be overwhelming even for experienced researchers. Three years ago, the Allen Institute for Artificial Intelligence launched semanticscholar.org to understand and address the information needs of researchers. In this talk, I start by highlighting some of the lessons we learned from our 2M monthly actively users, and some of the key differences between academic and industrial research. Then, I describe three complementary directions for analyzing the scientific literature at scale. In the first direction, we extract meaningful structures such as entities, relationships and figures. In the second direction, we establish connections between different artifacts in the literature to facilitate navigation and enable complex querying capabilities. In the third direction, we try to address controversial questions in the literature by quantifying observable attributes at a large scale. I conclude with a short list of under-explored research opportunities with high potential in this domain.
Bio: Waleed Ammar is a senior research scientist at the Allen Institute for Artificial Intelligence where he leads the research efforts in the semantic scholar project. He is interested in developing NLP models with practical applications, especially in the scientific and medical domains and other data-constrained scenarios. Before pursuing his PhD at Carnegie Mellon University, Waleed an engineer at the machine translation group at MSR, a web developer at eSpace technologies, and a teaching assistant at Alexandria University. Waleed co-hosts the NLP highlights podcast with Matt Gardner.
Biography: Waleed Ammar is a senior research scientist at the Allen Institute for Artificial Intelligence where he leads the research efforts in the semantic scholar project. He is interested in developing NLP models with practical applications, especially in the scientific and medical domains and other data-constrained scenarios. Before pursuing his PhD at Carnegie Mellon University, Waleed an engineer at the machine translation group at MSR, a web developer at eSpace technologies, and a teaching assistant at Alexandria University. Waleed co-hosts the NLP highlights podcast with Matt Gardner.
Host: Xusen Yin
More Info: http://nlg.isi.edu/nl-seminar/
Webcast: https://bluejeans.com/s/vEMME/Location: Information Science Institute (ISI) - 6th Floor Conf Rm-CR# 689
WebCast Link: https://bluejeans.com/s/vEMME/
Audiences: Everyone Is Invited
Contact: Peter Zamar
Event Link: http://nlg.isi.edu/nl-seminar/
-
USC Viterbi Data Analytics Boot Camp
Mon, Nov 12, 2018
Executive Education
Conferences, Lectures, & Seminars
Abstract: What you will learn:
- Students will learn the fundamental and specialized skills necessary to pursue a career or advance in the booming field of data analytics, including Python, JavaScript, Advanced Excel, SQL Databases and more.
- Students are equipped with the technical skills needed to translate data into competitive insights in the workplace, leading to career advancement opportunities.
- Students receive a hands-on, classroom learning experience, conducting robust analytics on a host of real-world problems.
- Students working to change career paths receive career-planning assistance, including industry speakers and company-led events, resume, Linkedln and portfolio support, and interview preparation.
More Info: https://viterbiexeced.usc.edu/engineering-program-areas/computer-science/usc-viterbi-data-analytics-boot-camp/
Audiences: Registered Attendees
Contact: Corporate & Professional Programs
-
CS Colloquium: Ram D. Sriram (NIST) - Explorations in Artificial Intelligence: A Personal Journey
Mon, Nov 12, 2018 @ 11:00 AM - 12:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ram D. Sriram, National Institute of Standards and Technology
Talk Title: Explorations in Artificial Intelligence: A Personal Journey
Series: Computer Science Colloquium
Abstract: My first exposure to Artificial Intelligence (AI) was in the summer of 1981, when Carnegie Mellon University was tasked with the development of a knowledge-based expert system (KBES) to aid in the trouble shooting of the Atlanta People Mover. I was a student member of this team and went on to do my dissertation on AI in Design. Later, I joined MIT as an assistant professor (in 1986) and with my students built one of the most comprehensive computational frameworks for Internet-based collaborative design -“ called DICE. The DICE framework introduced several novel concepts in AI, including an active object-oriented blackboard, constraint satisfaction using asynchronous teams, merging qualitative geometry with traditional modeling, knowledge representation schemes for product and process models, and design rationale. In 1994, I moved to NIST and continued work on knowledge representation for entire product life cycle until 2010, when I took over as the chief of Software and Systems Division. Here, I have provided technical leadership for several AI projects, which include extending deep learning techniques in biomedical image processing, extracting protein-protein interaction sentences from documents, developing a novel natural language term extraction system based on Sanskrit, and applying Category Theory for AI knowledge representation. In this talk, I will describe my journey over nearly four decades with a particular focus on my recent work at NIST on knowledge representation, machine learning, and natural language processing.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Ram D. Sriram is currently the chief of the Software and Systems Division, Information Technology Laboratory, at the National Institute of Standards and Technology (NIST). Before joining the Software and Systems Division, Sriram was the leader of the Design and Process group in the Manufacturing Systems Integration Division, Manufacturing Engineering Laboratory, where he conducted research on standards for interoperability of computer-aided design systems. Prior to joining NIST, he was on the engineering faculty (1986-1994) at the Massachusetts Institute of Technology (MIT) and was instrumental in setting up the Intelligent Engineering Systems Laboratory. Sriram has co-authored or authored more than 250 publications, including several books on artificial intelligence. Sriram was a founding co-editor of the International Journal for AI in Engineering. Sriram received several awards including: an NSF's Presidential Young Investigator Award (1989); ASME Design Automation Award (2011); ASME CIE Distinguished Service Award (2014); the Washington Academy of Sciences' Distinguished Career in Engineering Sciences Award (2015); ASME CIE division's Lifetime Achievement Award (2016); and CMU CEE Lt. Col. Christopher Raible Distinguished Public Service Award (2018). Sriram is a Fellow of ASME, AAAS, IEEE and Washington Academy of Sciences, a Member (life) of ACM and a Senior Member (life) of AAAI. Sriram has a B.Tech. from IIT, Madras, India, and an M.S. and a Ph.D. from Carnegie Mellon University, Pittsburgh, USA.
Host: Computer Science Department
Location: Olin Hall of Engineering (OHE) - 100D
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Seminars in Biomedical Engineering
Mon, Nov 12, 2018 @ 12:30 PM - 01:50 PM
Conferences, Lectures, & Seminars
Speaker: Kaustabh Ghosh, PhD, Associate Professor, Department of Bioengineering, Division of Biomedical Sciences, and Program in Cell, Molecular and Developmental Biology University of California, Riverside
Talk Title: Learning the Hard Way: Role of Vascular Stiffening in Inflammatory Retinal Diseases
Host: Qifa Zhou
More Information: Ghosh USC BME Abstract.pdf
Location: Olin Hall of Engineering (OHE) - 122
Audiences: Everyone Is Invited
Contact: Mischalgrace Diasanta
-
Fall 2018 Joint CSC@USC/CommNetS-MHI Seminar Series
Mon, Nov 12, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Munther Dahleh, MIT
Talk Title: A Marketplace for Data: An Algorithmic Solution
Abstract: In this work, we aim to create a data marketplace; a robust real-time matching mechanism to efficiently buy and sell training data for Machine Learning tasks. While the monetization of data and pre-trained models is an essential focus of industry today, there does not exist a market mechanism to price training data and match buyers to vendors while still addressing the associated (computational and other) complexity. The challenge in creating such a market stems from the very nature of data as an asset: it is freely replicable; its value is inherently combinatorial due to correlation with signal in other data; prediction tasks and the value of accuracy vary widely; usefulness of training data is difficult to verify a priori without first applying it to a prediction task. As our main contributions we: propose a mathematical model for a two-sided data market and formally define the key associated challenges; construct algorithms for such a market to function and rigorously prove how they meet the challenges defined. We highlight two technical contributions: a new notion of fairness required for cooperative games with freely replicable goods; a truthful, zero regret mechanism for auctioning a particular class of combinatorial goods based on utilizing Myerson's payment function and the Multiplicative Weights algorithm. These might be of independent interest.
This is a joint work with Anish Agarwal, Tuhin Sarkar, and Devavrat Shah.
Biography: Munther A. Dahleh received his PhD degree from Rice University, Houston, TX, in 1987 in Electrical and Computer Engineering. Since then, he has been with the Department of Electrical Engineering and Computer Science (EECS), MIT, Cambridge, MA, where he is now the William A. Coolidge Professor of EECS. He is also a faculty affiliate of the Sloan School of Management. He is the founding director of the newly formed MIT Institute for Data, Systems, and Society (IDSS). Previously, he held the positions of Associate Department Head of EECS, Acting Director of the Engineering Systems Division, and Acting Director of the Laboratory for Information and Decision Systems. He was a visiting Professor at the Department of Electrical Engineering, California Institute of Technology, Pasadena, CA, for the Spring of 1993. He has consulted for various national research laboratories and companies. Dr. Dahleh is interested in Networked Systems with applications to Social and Economic Networks, financial networks, Transportation Networks, Neural Networks, and the Power Grid. Specifically, he focuses on the development of foundational theory necessary to understand, monitor, and control systemic risk in interconnected systems. His work draws from various fields including game theory, optimal control, distributed optimization, information theory, and distributed learning. His collaborations include faculty from all five schools at MIT. Dr. Dahleh is the co-author (with Ignacio Diaz-Bobillo) of the book Control of Uncertain Systems: A Linear Programming Approach, published by Prentice-Hall, and the co-author (with Nicola Elia) of the book Computational Methods for Controller Design, published by Springer. He is four-time recipient of the George Axelby outstanding paper award for best paper in IEEE Transactions on Automatic Control. He is also the recipient of the Donald P. Eckman award from the American Control Council in 1993 for the best control engineer under 35. He is a fellow of IEEE and IFAC. He has given many keynote lectures at major conferences.
Host: Ketan Savla, ksavla@usc.edu
More Info: http://csc.usc.edu/seminars/2018Fall/dahleh.html
More Information: 18.11.12_Dahleh_MIT-CSC Seminar.pdf
Location: 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
Event Link: http://csc.usc.edu/seminars/2018Fall/dahleh.html
-
Trusted Inference Engine: Preventing Neural Network Exfiltration in Hardware Devices
Tue, Nov 13, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Michel A. Kinsy, Boston University
Talk Title: Trusted Inference Engine: Preventing Neural Network Exfiltration in Hardware Devices
Abstract: Companies, in their push to incorporate artificial intelligence - in particular, machine learning - into their Internet of Things (IoT), system-on-chip (SoC), and automotive applications, will have to address a number of design challenges related to the secure deployment of artificial intelligence learning models and techniques. Machine learning (ML) models are often trained using private datasets that are very expensive to collect, or highly sensitive, using large amounts of computing power. The models are commonly exposed either through online APIs, or used in hardware devices deployed in the field or given to the end users. This gives incentives to adversaries to attempt to steal these ML models as a proxy for gathering datasets. While API-based model exfiltration has been studied before, the theft and protection of machine learning models on hardware devices have not been explored as of now. In this work, we examine this important aspect of the design and deployment of ML models. We illustrate how an attacker may acquire either the model or the model architecture through memory probing, side-channels, or crafted input attacks, and propose power-efficient obfuscation as an alternative to encryption, and timing side-channel countermeasures.
Biography: Michel A. Kinsy is an Assistant Professor in the Department of Electrical and Computer Engineering at Boston University (BU), where he directs the Adaptive and Secure Computing Systems (ASCS) Laboratory. He focuses his research on computer architecture, hardware-level security, neural network accelerator designs, and cyber-physical systems. Dr. Kinsy is an MIT Presidential Fellow, the 2018 MWSCAS Myril B. Reed Best Paper Award Recipient, DFT'17 Best Paper Award Finalist, and FPL'11 Tools and Open-Source Community Service Award Recipient. He earned his PhD in Electrical Engineering and Computer Science in 2013 from the Massachusetts Institute of Technology. His doctoral work in algorithms to emulate and control large-scale power systems at the microsecond resolution inspired further research by the MIT spin-off Typhoon HIL, Inc. Before joining the BU faculty, Dr. Kinsy was an assistant professor in the Department of Computer and Information Systems at the University of Oregon, where he directed the Computer Architecture and Embedded Systems (CAES) Laboratory. From 2013 to 2014, he was a Member of the Technical Staff at the MIT Lincoln Laboratory.
Host: Xuehai Qian, xuehai.qian@usc.edu
More Information: 18.11.13 Michel Kinsy_CENG Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
-
Annual Grodins Keynote Lecture
Tue, Nov 13, 2018 @ 03:00 PM - 05:00 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Kullervo Hynynen, M.Sc., PhD, Professor, University of Toronto (Department of Medical Biophysics and Institute of Biomaterials and Biomedical Engineering)
Talk Title: Non-Invasive Brain Treatments Using Image Guided and Modulated Ultrasound Beams
Series: Annual Grodins Keynote Lecture
Abstract: Non-invasive brain treatments using image-guided and modulated ultrasound beams When combined with imaging-guidance focused ultrasound (FUS) provides means for localized delivery of mechanical energy deep into tissues. This focal energy deposition can modify tissue function via thermal or mechanical interactions with the tissue. MRI-guided hemi-spherical phased array technology with CT based beam modulation has made FUS treatments of brain through intact skull possible in the clinical setting. Thermal ablation of a target in a thalamus has been shown to be effective in the treatment of essential tremor and is now FDA approved. The impact of an ultrasound exposure can be potentiated by intravascular microbubbles that can enhance blood-brain barrier (BBB) permeability for a wide variety of molecules, particles and even cells. The ability to modulate the BBB has been shown to be effective in treatments of many deceases in animal models with initial patient trials showing clinical feasibility. In this talk, the progress in utilizing ultrasound phased array technology for brain treatments will be reviewed and its further potential discussed.
Biography: Dr. Hynynen received his PhD from the University of Aberdeen, United Kingdom. After completing his postdoctoral training in biomedical ultrasound also at the University of Aberdeen, he accepted a faculty position at the University of Arizona. After, he joined the faculty at the Harvard Medical School, and Brigham and Women's Hospital in Boston, MA. There he reached the rank of full Professor, and founded and directed the Focused Ultrasound Laboratory. In 2006 he moved to the University of Toronto. He is currently the Director of Physical Sciences Platform at the Sunnybrook Research Institute and a Professor in the Department of Medical Biophysics and Cross Appointed Professor at the Institute of Biomaterials & Biomedical Engineering (IBBME) at the University of Toronto. His research focuses on utilizing focused ultrasound for non-invasive, image-guided interventions. His work in the brain spans from developing devices and methods for focal tissue ablation in clinical testing to research for targeted drug and cell delivery and stroke treatments.
Host: Professor Kirk Shung
More Information: 2018 Fred S. Grodins Keynote Speaker Kullervo Hynynen.pdf
Location: Michelson Center for Convergent Bioscience (MCB) - 101
Audiences: BME graduate students, Faculty, contact department if interested (213-740-7237)
Contact: Mischalgrace Diasanta
-
Epstein Institute Seminar - ISE 651
Tue, Nov 13, 2018 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Hui Yang, Associate Professor, Penn State
Talk Title: Sensor-based Modeling and Control of Nonlinear Dynamics for Advanced Manufacturing and Smart Health
Host: Professor Julie Higle
More Information: November 13, 2018.pdf
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Everyone Is Invited
Contact: Grace Owh
-
CAIS Seminar: Dr. Sanmay Das (Washington University in St. Louis) - Allocating Scarce Societal Resources Based on Predictions of Outcomes
Tue, Nov 13, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Sanmay Das, Washington University in St. Louis
Talk Title: Allocating Scarce Societal Resources Based on Predictions of Outcomes
Series: USC Center for Artificial Intelligence in Society (CAIS) Seminar Series
Abstract: Demand for resources that are collectively controlled or regulated by society, like social services or organs for transplantation, typically far outstrips supply. How should these scarce resources be allocated? In this talk, Dr. Das will discuss his work on weighted matching and assignment in two domains, namely living donor kidney transplantation and provision of services to homeless households. His focus will be on how effective prediction of the outcomes of matches has the potential to dramatically improve social welfare both by allowing for richer mechanisms and by improving allocations. He will also discuss implications for equity and justice.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Dr. Sanmay Das is an associate professor in Computer Science and Engineering and the chair of the steering committee of the newly formed Division of Computational and Data Sciences at Washington University in St. Louis. He is vice-chair of the ACM Special Interest Group on Artificial Intelligence and a member of the board of directors of the International Foundation for Autonomous Agents and Multiagent Systems. Dr. Das has served as program co-chair of the AAMAS and AMMA conferences, and has been recognized with awards for research and teaching, including an NSF CAREER Award and the Department Chair Award for Outstanding Teaching at Washington University.
Host: Milind Tambe
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Mork Family Department of Chemical Engineering and Materials Science Seminar - Distinguished Lecture Series
Tue, Nov 13, 2018 @ 04:00 PM - 05:20 PM
Mork Family Department of Chemical Engineering and Materials Science
Conferences, Lectures, & Seminars
Speaker: Prof. Matthew Lazzara, Departments of Chemical Engineering and Biomedical Engineering, University of Virginia
Talk Title: Applications of mechanistic and data-driven models to problems in cell signaling
Abstract: Cells are signaled to proliferate, migrate, differentiate, and die through the action of receptors, membrane-spanning proteins that translate extracellular ligand binding events into cellular decisions by initiating networks of intracellular biochemical reactions. The complexity of these problems is ideal for, and often requires, application of computational modeling approaches to interpret data, predict system performance, and generate new hypotheses. However, the specific modeling approach must be tailored to the type and scope of problem at hand. While some problems are sufficiently circumscribed for use of familiar mechanistic governing equations, others are more easily tackled by first seeking statistical inferences from large data sets for which mechanistic governing equations are unknown. This seminar will cover examples of both types of problems. In the first part of the talk, I will describe our lab s efforts to develop experimentally validated mechanistic models of the regulation of epidermal growth factor receptor (EGFR) signaling by protein tyrosine phosphatases, focusing on the coupling between receptor endocytosis and dephosphorylation and on phosphatase-mediated regulation of the persistence of EGFR-driven signaling protein complexes. In the second part of the talk, I will describe our recent efforts to apply data-driven modeling approaches for the rational design of combination therapies for pancreas and brain cancers.
Biography: Matthew Lazzara received a B.S. in Chemical Engineering (with highest honors) from the University of Florida and a Ph.D. in Chemical Engineering from the Massachusetts Institute of Technology, where he trained in the lab of William Deen. He remained at MIT for postdoctoral studies in the lab of Douglas Lauffenburger and was the recipient of an NIH Ruth L. Kirschstein National Research Service Award Postdoctoral Fellowship. Dr. Lazzara is presently Associate Professor of Chemical Engineering and holds a joint appointment in the Department of Biomedical Engineering. Work in the Lazzara Lab employs a combination of experimental and computational methods to study problems in cell signaling, the complex biochemical process cells use to make decisions. Current projects focus on the rational (model-driven) identification of combination therapies for cancer and on fundamental studies of the spatiotemporal regulation of cell signaling by phosphatases and receptor trafficking. The lab's work is funded by grants from the American Cancer Society, National Science Foundation, and National Institutes of Health. Dr. Lazzara is also the recipient of several teaching awards, including the S. Reid Warren, Jr. Award and the Outstanding Faculty Award of the AIChE Delaware Valley, and is a member of the Board of Directors of the Museum of Science and Industry in Tampa, FL.
Host: Prof. Nicholas Graham
Location: John Stauffer Science Lecture Hall (SLH) - 200
Audiences: Everyone Is Invited
Contact: Karen Woo/Mork Family
-
Astani Civil and Environmental Engineering Seminar
Wed, Nov 14, 2018 @ 11:30 AM - 12:30 PM
Sonny Astani Department of Civil and Environmental Engineering
Conferences, Lectures, & Seminars
Speaker: Mohammed Alnaggar, Ph.D., Rensselaer Polytechnic University
Talk Title: Predicting Reinforced Concrete Aging and Deterioration: Experiments or Modeling?
Abstract: See attachment.
Host: Dr. Parick Lynett and Dr. Bora Gencturk
More Information: Nov 14 Mohammed Alnaggar Civil Engineering Seminar.pdf
Location: Ray R. Irani Hall (RRI) - 101.
Audiences: Everyone Is Invited
Contact: Evangeline Reyes
-
W.V.T. RUSCH ENGINEERING HONORS COLLOQUIUM
Fri, Nov 16, 2018 @ 01:00 PM - 01:50 PM
USC Viterbi School of Engineering
Conferences, Lectures, & Seminars
Speaker: Dr. Garret Reisman, USC Professor of Astronautical Engineering, former NASA astronaut, former SpaceX Director of Space Operations
Talk Title: Human Spaceflight - Recent Past and Near Future
Host: EHP and Dr. Prata
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Amanda McCraven
-
MASCLE Machine Learning Seminar: Ahmad Beirami (Electronic Arts) - Powering Games with Data & AI
Fri, Nov 16, 2018 @ 02:00 PM - 03:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ahmad Beirami, Electronic Arts
Talk Title: Powering Games with Data & AI
Series: Computer Science Colloquium
Abstract: At EA Digital Platform - Data & AI, we build centralized data-driven and AI-assisted services that power games. In this talk, we begin with an introduction to our data infrastructure and AI platform, that constitute a solid bedrock for solving practical AI problems. We overview several AI applications built on this platform to improve the gameplay experience for hundreds of millions across the globe in addition to contributing scientifically to the research community. We finish with a discussion on the open problems that we are currently tackling.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Ahmad Beirami is a research scientist with Electronic Arts (EA) leading fundamental research and development on training artificial agents in multi-agent systems. His research interests broadly include AI, machine learning, statistics, information theory, and networks. Prior to joining EA in 2018, he held postdoctoral fellow positions at Duke, MIT, and Harvard. He is the recipient of the 2015 Sigma Xi Best PhD Thesis Award from Georgia Tech.
Host: Yan Liu, USC Machine Learning Center
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
Intermittent Computing Systems
Fri, Nov 16, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Brandon Lucia, Carnegie Mellon University
Talk Title: Intermittent Computing Systems
Abstract: The emergence of extremely low-power computing components and efficient energy-harvesting power systems has led to the creation of computer systems that operate using tiny amounts of energy scavenged from their environment. These devices create opportunities for systems where batteries and tethered power are inapplicable: sensors deeply embedded in pervasive civil infrastructure, in-body health monitors, and devices in extreme environments like glaciers, volcanoes, and space. The key challenge is that these devices operate only intermittently, as energy is available, requiring both hardware and software to tolerate power failures that may happen hundreds of times per second. This talk will describe the landscape of intermittent computing systems. I will focus on new programming and execution models that are robust to arbitrarily frequent power failures. In particular, the talk will focus on three models, DINO, Chain, and Alpaca, which we developed as a progression toward a system that is simple to program and offers reliable intermittent operation. I will then discuss how these models interact with our latest hardware platform, Capybara, enabling applications to dynamically re-configure the amount of energy continuously required by a region of code and supporting modal energy demands with a single hardware mechanism. I will close with a discussion of recent and upcoming deployment efforts for our intermittent systems work.
Biography: Brandon Lucia is an Assistant Professor of Electrical and Computer Engineering at Carnegie Mellon University. Lucia's lab's work spans programming languages, software and hardware computer systems, and computer architecture. Lucia's lab is defining the area of intermittent computing on energy-harvesting devices, and working on future reliable, efficient parallel computing systems, especially at the edge. Lucia's work has been recognized with a 2018 NSF CAREER Award, the 2018 ASPLOS Best Paper Award, three IEEE MICRO Top Picks in Computer Architecture, a 2015 OOPSLA Best Paper Award, the 2015 Bell Labs Prize, a 2016 Google Faculty Award, and an appointment to the DARPA ISAT study group. His website is https://brandonlucia.com and more information on his lab, which is supported by NSF, Intel, Google, SRC, DARPA, the Kavcic-Moura Fund, and Disney Research, is available at http://intermittent.systems.
Host: Xuehai Qian, xuehai.qian@usc.edu
More Information: 18.11.16 Brandon Lucia_CENG Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 248
Audiences: Everyone Is Invited
Contact: Brienne Moore
-
Seminars in Biomedical Engineering
Mon, Nov 19, 2018 @ 12:30 PM - 01:50 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Benjamin Xu, MD, USC Keck School of Medicine, Assistant Professor Of Clinical Ophthalmology
Talk Title: AI for glaucoma study
Host: Qifa Zhou
Location: Olin Hall of Engineering (OHE) - 122
Audiences: Everyone Is Invited
Contact: Mischalgrace Diasanta
-
**No Epstein Seminar, ISE 651 This Week (Happy Thanksgiving)**
Tue, Nov 20, 2018
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Audiences: Everyone Is Invited
Contact: Grace Owh
-
Seminars in Biomedical Engineering
Mon, Nov 26, 2018 @ 12:30 PM - 01:50 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Kimberly Gokoffski, USC Keck School of Medicine, Assistant Professor of Clinical Ophthalmology
Talk Title: Retina cell growth along with electrical field stimulation
Host: Qifa Zhou
Location: Olin Hall of Engineering (OHE) - 122
Audiences: Everyone Is Invited
Contact: Mischalgrace Diasanta
-
Fall 2018 Joint CSC@USC/CommNetS-MHI Seminar Series
Mon, Nov 26, 2018 @ 02:00 PM - 03:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Geir Dullerud, University of Illinois Urbana-Champaign
Talk Title: Automata-switched systems, decentralized control, and team games
Abstract: This seminar is inspired from a practical perspective by recent advances in computing, sensing and networking hardware that make reconfigurable multiagent systems both technologically and economically feasible on a widespread scale. Switching is a common feature in systems that are comprised of interacting software and physical processes, and in this talk we will focus on a special type of hybrid model called an automaton-switched linear system. These models are closely related to Markovian jump linear systems, and contain both discrete and continuous states, where discrete states evolve according to automata, or more general transition systems, and continuous states evolve according to linear dynamics influenced by the discrete states. We will discuss how such systems can be automatically analyzed using ideas from control theory and semidefinite programming, and will provide solutions to several synthesis problems in this framework, including for instance the long-studied moving horizon problem, and the decentralized control problem for systems with nested structure. We will also present results on a particular class of team games in which players have incomplete model knowledge individually, but jointly know the global system dynamics. The HoTDeC multi-vehicle testbed will also be presented, along with implementations of the above results on indoor UAVs.
Biography: Geir E. Dullerud is the W. Grafton and Lillian B. Wilkins Professor in Mechanical Engineering at the University of Illinois at Urbana-Champaign. There he is also a member of the Coordinated Science Laboratory, where he is Director of the Decision and Control Laboratory (21 faculty); he is an Affiliate Professor of both Computer Science, and Electrical and Computer Engineering. He has held visiting positions in Electrical Engineering KTH, Stockholm (2013), and Aeronautics and Astronautics, Stanford University (2005-2006). Earlier he was on faculty in Applied Mathematics at the University of Waterloo (1996-1998), after being a Research Fellow at the California Institute of Technology (1994- 1995), in the Control and Dynamical Systems Department. He holds a PhD in Engineering from Cambridge University. He has published two books: A Course in Robust Control Theory, Texts in Applied Mathematics, Springer, 2000, and Control of Uncertain Sampled-data Systems, Birkhauser 1996. His areas of current research interest include convex optimization in control, cyber-physical system security, cooperative robotics, stochastic simulation, and hybrid dynamical systems. In 1999 he received the CAREER Award from the National Science Foundation, and in 2005 the Xerox Faculty Research Award at UIUC. He is a Fellow of both IEEE (2008) and ASME (2011). He is the General Chair of the upcoming IFAC workshop Distributed Estimation and Control in Networked Systems (NECSYS) to be held in Chicago in 2019.
Host: Mihailo Jovanovic, mihailo@usc.edu
More Info: http://csc.usc.edu/seminars/2018Fall/dullerud.html
More Information: 18.11.26_Geir Dullerud CSCUSC Seminar.pdf
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Brienne Moore
Event Link: http://csc.usc.edu/seminars/2018Fall/dullerud.html
-
Epstein Institute Seminar - ISE 651
Tue, Nov 27, 2018 @ 03:30 PM - 04:50 PM
Daniel J. Epstein Department of Industrial and Systems Engineering
Conferences, Lectures, & Seminars
Talk Title: Last Class Session
Location: Ethel Percy Andrus Gerontology Center (GER) - 206
Audiences: Department Only
Contact: Grace Owh
-
MASCLE Machine Learning Seminar: William Wang (UCSB) – Learning to Generate Language and Actions with Structured Agents
Tue, Nov 27, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: William Wang, University of California, Santa Barbara
Talk Title: Learning to Generate Language and Actions with Structured Agents
Series: Machine Learning Seminar Series
Abstract: A major challenge in Natural Language Processing is to teach machines to generate natural language and actions. However, existing deep learning approaches to language generation do not impose structural constraints in the generation process, often producing low-quality results. In this context, we will introduce our attempt of imposing structural constraints for video captioning via hierarchical reinforcement learning. Moreover, we observe that most of the automated metrics for generation could be gamed, and therefore, we propose an adversarial reward learning method to automatically learn the reward via inverse reinforcement learning. Furthermore, I will discuss our recent attempts in connecting language and vision to actions via a language grounding task for robot navigation, and introduce new algorithms on scheduled policy optimization and combining model-free and model-based reinforcement learning. I will conclude by introducing other exciting research projects at UCSB's NLP Group.
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: William Wang is an Assistant Professor in the Department of Computer Science at the University of California, Santa Barbara. He received his PhD from School of Computer Science, Carnegie Mellon University in 2016. He has broad interests in machine learning approaches to data science, including natural language processing, statistical relational learning, information extraction, computational social science, dialogue, and vision. He directs UCSB's NLP Group (nlp.cs.ucsb.edu): in two years, UCSB advanced in the NLP area from an undefined ranking position to top 3 in 2018 according CSRankings.org. He has published more than 60 papers at leading NLP/AI/ML conferences and journals, and received best paper awards (or nominations) at ASRU 2013, CIKM 2013, and EMNLP 2015, a DARPA Young Faculty Award (Class of 2018), two IBM Faculty Awards in 2017 and 2018, a Facebook Research Award in 2018, an Adobe Research Award in 2018, and the Richard King Mellon Presidential Fellowship in 2011. He served as an Area Chair for NAACL, ACL, EMNLP, and AAAI. He is an alumnus of Columbia University, Yahoo! Labs, Microsoft Research Redmond, and University of Southern California. In addition to research, William enjoys writing scientific articles that impact the broader online community: his microblog @çå¨å» has 110,000+ followers and more than 2,000,000 views each month. His work and opinions appear at major international tech media outlets such as Wired, VICE, Fast Company, NASDAQ, The Next Web, Law.com, and Mental Floss.
Host: Yan Liu, USC Machine Learning Center
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Chad Jenkins (University of Michigan) - Semantic Robot Programming... and Making the World a Better Place Too
Tue, Nov 27, 2018 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Chad Jenkins, University of Michigan
Talk Title: Semantic Robot Programming...and Making the World a Better Place Too
Series: CS Colloquium
Abstract: The visions of interconnected heterogeneous autonomous robots in widespread use are a coming reality that will reshape our world. Similar to "app stores" for modern computing, people at varying levels of technical background will contribute to "robot app stores" as designers and developers. However, current paradigms to program robots beyond simple cases remains inaccessible to all but the most sophisticated of developers and researchers. In order for people to fluently program autonomous robots, a robot must be able to interpret user instructions that accord with that user's model of the world. The challenge is that many aspects of such a model are difficult or impossible for the robot to sense directly. We posit a critical missing component is the grounding of semantic symbols in a manner that addresses both uncertainty in low-level robot perception and intentionality in high-level reasoning. Such a grounding will enable robots to fluidly work with human collaborators to perform tasks that require extended goal-directed autonomy.
I will present our efforts towards accessible and general methods of robot programming from the demonstrations of human users. Our recent work has focused on Semantic Robot Programming (SRP), a declarative paradigm for robot programming by demonstration that builds on semantic mapping. In contrast to procedural methods for motion imitation in configuration space, SRP is suited to generalize user demonstrations of goal scenes in workspace, such as for manipulation in cluttered environments. SRP extends our efforts to crowdsource robot learning from demonstration at scale through messaging protocols suited to web/cloud robotics. With such scaling or robotics in mind, prospects for cultivating both equal opportunity and technological excellence will be discussed in the context of broadening and strengthening Title IX.
Biography: Odest Chadwicke Jenkins, Ph.D., is an Associate Professor of Computer Science and Engineering at the University of Michigan. Prof. Jenkins earned his B.S. in Computer Science and Mathematics at Alma College (1996), M.S. in Computer Science at Georgia Tech (1998), and Ph.D. in Computer Science at the University of Southern California (2003). He previously served on the faculty of Brown University in Computer Science (2004-15). His research addresses problems in interactive robotics and human-robot interaction, primarily focused on mobile manipulation, robot perception, and robot learning from demonstration. He is a founder of the Robot Web Tools open-source robotics organization. Prof. Jenkins' work has been recognized by a Sloan Research Fellow, a Presidential Early Career Award for Scientists and Engineers (PECASE), and Young Investigator awards from the Office of Naval Research, the Air Force Office of Scientific Research, and the National Science Foundation. Prof. Jenkins is currently serving as the Editor-in-Chief for the ACM Transactions on Human-Robot Interaction
Host: Maja Mataric
Location: Ronald Tutor Hall of Engineering (RTH) - 105
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Decentralized Signal Processing and Distributed Control for Collaborative Autonomous Sensor Networks
Wed, Nov 28, 2018 @ 12:00 PM - 01:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Ryan Alan Goldhahn & Priyadip Ray, Lawrence Livermore National Laboratory
Talk Title: Decentralized Signal Processing and Distributed Control for Collaborative Autonomous Sensor Networks
Series: Center for Cyber-Physical Systems and Internet of Things
Abstract: Collaborative autonomous sensor networks have recently been used in many applications including inspection, law enforcement, search and rescue, and national security. They offer scalable, low-cost solutions which are robust to the loss of multiple sensors in hostile or dangerous environments. While often comprised of less capable sensors, the performance of a large network can approach the performance of far more capable and expensive platforms if nodes are effectively coordinating their sensing actions and data processing. This talk will summarize work to date at LLNL on distributed signal processing and decentralized optimization algorithms for collaborative autonomous sensor networks, focusing on ADMM-based solutions for detection/estimation problems and sequential and/or greedy optimization solutions which maximize submodular functions such as mutual information.
Biography: Ryan Goldhahn holds a Ph.D. in electrical engineering from Duke University with a focus in statistical and model-based signal processing. Ryan joined the NATO Centre for Maritime Research and Experimentation (CMRE) as a researcher in 2010 and later as the project lead for an effort to use multiple unmanned underwater vehicles (UUVs) to detect and track submarines using multi-static active sonar. In this work he developed collaborative autonomous behaviors to optimally reposition UUVs to improve tracking performance without human intervention. He led several experiments at sea with submarines from multiple NATO nations. At LLNL Ryan has continued to work and lead projects in collaborative autonomy and model-based and statistical signal processing in various applications. He has specifically focused on decentralized detection/estimation/tracking and optimization algorithms for autonomous sensor networks.
Priyadip Ray received a Ph.D. degree in electrical engineering from Syracuse University in 2009. His Ph.D. dissertation received the Syracuse University All-University Doctoral Prize. Prior to joining LLNL, Dr. Ray was an assistant professor at the Indian Institute of Technology (IIT), Kharagpur, India where he supervised a research group of approximately 10 scholars in the areas of statistical signal processing, wireless communications, optimization, machine learning and Bayesian non-parametrics. Prior to this he was a research scientist with the Department of Electrical and Computer Engineering at Duke University. Dr. Ray has published close to 40 research articles in various highly-rated journals and conference proceedings and is also a reviewer for leading journals in the areas of statistical signal processing, wireless communications and data science. At LLNL, Dr. Ray has been the PI/Co-I on multiple LDRDs as well as a DARPA funded research effort in the areas of machine learning for healthcare and collaborative autonomy.
Host: Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Talyia White
-
AME Seminar
Wed, Nov 28, 2018 @ 03:30 PM - 04:30 PM
Aerospace and Mechanical Engineering
Conferences, Lectures, & Seminars
Speaker: Heather Culbertson, USC
Talk Title: Can You Feel It? Haptics for Realism and Virtual Communication
Abstract: The haptic (touch) sensations felt when interacting with the physical world create a rich and varied impression of objects and their environment. Humans can a gather significant amount of information through touch with their environment, allowing them to assess object properties and qualities, dexterously handle objects, and communicate social cues and emotions. However, humans are spending significantly more time in the virtual world and are increasingly interacting with people and objects through a digital medium. Unfortunately, digital interactions remain unsatisfying and limited, representing the human as having only two sensory inputs: visual and auditory.
This talk will focus on the investigation of haptic devices and rendering algorithms to provide humans with touch feedback when communicating through a computer. I will present a background on the sense of touch and illustrate how we can leverage this knowledge to design haptic devices and rendering systems that allow the human to virtually communicate in a natural and intuitive way. I will then discuss our work in creating realistic haptics in virtual reality through both data-driven modeling and novel haptic hardware.
Biography: Heather Culbertson is a WiSE Gabilan Assistant Professor of Computer Science and Aerospace and Mechanical Engineering at the University of Southern California where she directs the Haptics Robotics and Virtual Interaction (HaRVI) Lab. Previously, she was a research scientist in the Department of Mechanical Engineering at Stanford University. She received her PhD in the Department of Mechanical Engineering and Applied Mechanics (MEAM) at the University of Pennsylvania in 2015, a MS degree in MEAM at the University of Pennsylvania in 2013 and earned a BS degree in mechanical engineering at the University of Nevada, Reno in 2010. She is currently serving as the Vice-Chair for Information Dissemination for the IEEE Technical Committee on Haptics. Her awards include a citation for meritorious service as a reviewer for the IEEE Transactions on Haptics, Best Paper at UIST 2017, and the Best Hands-On Demonstration Award at IEEE World Haptics 2013.
Host: Julian Domaradzki
More Info: https://ame.usc.edu/seminars/
Location: Seaver Science Library (SSL) - 150
Audiences: Everyone Is Invited
Contact: Tessa Yao
Event Link: https://ame.usc.edu/seminars/
-
CS Distinguished Lecture: Rodney Allen Brooks (MIT, iRobot, Rethink) - Steps Towards Super Intelligence
Wed, Nov 28, 2018 @ 05:00 PM - 06:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Rodney Allen Brooks, MIT, iRobot, Rethink
Talk Title: Steps Towards Super Intelligence
Series: CS Distinguished Lectures
Abstract: In his 1950 paper "Computing Machinery and Intelligence" Alan Turing estimated that sixty people working for fifty years should be able to program a computer (running at 1950 speed) to have human level intelligence. AI researchers have spent orders of magnitude more effort than that and are still not close. Why has AI been so hard and what are the problems that we might work on in order to make real progress to human level intelligence, or even the super intelligence that many pundits believe is just around the corner? This talk will discuss those steps we can take, what aspects we really still do not have much of a clue about, what we might be currently getting completely wrong, and why it all could be centuries away. Importantly the talk will make distinctions between research questions and barriers to technology adoption from research results, with a little speculation on things that might go wrong (spoiler alert: it is the mundane that will have the big consequences, not the Hollywood scenarios that the press and some academics love to talk about).
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Rodney Brooks earned Bachelors and Masters degrees in pure mathematics from Flinders University in South Australia. In 1977 he joined the Artificial Intelligence Lab at Stanford graduating with a PhD in computer science in 1981. After post-docs at Carnegie Mellow and MIT, and a faculty position back at Stanford he joined the MIT faculty at the Artificial Intelligence Laboratory there in 1984. He worked in computer vision, robotics, and artificial life. He became director of the AI Lab in 1997 and in 2003 he founded the Computer Science and Artificial Intelligence Lab, CSAIL, which is the largest lab at MIT with over 1,000 members. Along the way he started a software company in silicon valley, a boutique robotics venture capital fund, the company iRobot which has delivered tens of millions of home cleaning robots and many thousand ground robots to the US military, and more recently spent 10 years developing collaborative robots for manufacturing at Rethink Robotics. He retired from MIT In 2010, and currently advises companies large and small, including Toyota and their autonomous driving efforts. He is a member of the NAE and a Fellow of the American Academy of Arts and Sciences, and of the IEEE, ACM, AAAS, and AAAI. He writes at rodneybrooks.com/blog.
Host: Maja Mataric
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Ming Hsieh Institite: Emerging Trends Seminar Series
Thu, Nov 29, 2018 @ 11:00 AM - 12:00 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: C.-C. Jay Kuo, Distinguished Professor of Electrical Engineering-Systems and Computer Science, Ming Hsieh Department of Electrical Engineering
Talk Title: Interpretable Convolutional Neural Networks (CNNs) via Feedforward Design
Series: Emerging Trends
Abstract: Given a convolutional neural network (CNN) architecture, its network parameters are determined by backpropagation (BP). In contrast with the BP design, we propose a feedforward (FF) and interpretable design with the LeNet-5 as an illustrative example. The FF design is a data-centric approach that derives network parameters based on training data statistics layer by layer in one pass. To build the convolutional layers, we develop a new signal transform, called the Saab (Subspace approximation with adjusted bias) transform. The bias in filter weights is chosen to annihilate nonlinearity of the activation function. To build the fully-connected (FC) layers, we adopt a label-guided linear least squared regression (LSR) method. The FF design is more computationally efficient and robust against adversarial attacks than the traditional BP design. The classification performances of BP-designed and FF-designed CNNs on the MNIST and the CIFAR-10 datasets are compared. Finally, we comment on the relationship between BP and FF designs by examining their cross-entropy values at nodes of intermediate layers.
Biography: Dr. C.-C. Jay Kuo received his Ph.D. degree from the Massachusetts Institute of Technology in 1987. He is now with the University of Southern California (USC) as Director of the Media Communications Laboratory and Distinguished Professor of Electrical Engineering and Computer Science. His research interests are in the areas of media processing, compression and understanding. Dr. Kuo was the Editor-in-Chief for the IEEE Trans. on Information Forensics and Security in 2012-2014. Dr. Kuo received the 1992 National Science Foundation Young Investigator (NYI) Award, the 1993 National Science Foundation Presidential Faculty Fellow (PFF) Award, the 2010 Electronic Imaging Scientist of the Year Award, the 2010-11 Fulbright-Nokia Distinguished Chair in Information and Communications Technologies, the 2011 Pan Wen-Yuan Outstanding Research Award, the 2014 USC Northrop Grumman Excellence in Teaching Award, the 2016 USC Associates Award for Excellence in Teaching, the 2016 IEEE Computer Society Taylor L. Booth Education Award, the 2016 IEEE Circuits and Systems Society John Choma Education Award, the 2016 IS&T Raymond C. Bowman Award, and the 2017 IEEE Leon K. Kirchmayer Graduate Teaching Award. Dr. Kuo is a Fellow of AAAS, IEEE and SPIE. He has guided 147 students to their Ph.D. degrees and supervised 27 postdoctoral research fellows. Dr. Kuo is a co-author of 275 journal papers, 900 conference papers and 14 books.
Host: MHI
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Benjamin Paul
-
MHI Research & Technology Seminar
Thu, Nov 29, 2018 @ 01:00 PM - 02:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Ruirui Huang, Senior Staff Architect/Director of Cloud Architecture at Alibaba Cloud
Talk Title: Security Architectural Design and Challenges in the Cloud
Series: MHI Research & Technology Seminar
Abstract: I will introduce the multi-layered security architectural design of Alibaba Cloud. Specifically, several technologies and mechanisms in each layer will be highlighted and discussed in terms of their importance and the security purposes which they serve. Additionally, I will raise several security challenges in today's cloud computing domain, and discuss how one might address them today and if there is a better solution in the future.
Biography: Dr. Ruirui Huang is a Senior Staff Architect/Director of Cloud Architecture at Alibaba Cloud (US office, based in Seattle, WA). He is responsible for overseeing and developing the Alibaba Cloud Platform Architecture, with a focus on the secure cloud computing architecture. He is also the author of Alibaba Cloud Security White-paper which was published earlier in 2018. Prior joining Alibaba Cloud, he was a Senior Security Architect at Intel, responsible for multiple Server/PC/Mobile SoCs security architectural designs.
Dr. Ruirui Huang graduated with a Ph.D. degree from the ECE department of the Cornell University in 2013, with research works and interests in the field of computer architectural support of security, reliability, and availability in today's computing world.
Host: MHI
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Benjamin Paul
-
CS Tech Talk: DiDi Tech Talk with Dr. Fengmin Gong and Dr. Kevin Knight
Thu, Nov 29, 2018 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Fengmin Gong and Dr. Kevin Knight, Didi
Talk Title: Talk 1: AI for Transportation; Talk 2: The Moment When the Future Fell Asleep
Series: Computer Science Colloquium
Abstract: We are pleased to announce two talks during this colloquium.
Talk 1: Taming Technologies and Transforming Transportation
The world is at the dawn of a Fourth Industrial Revolution fueled by big data, AI, automation, vehicle electrification, and the sharing economy -“ and with this, comes both excitement for the prospect of changing society for the better, and fear of a possible threat to humanity.
Our mission at DiDi is to build a better journey, and we believe we can tame the revolution by designing and building technologies that meet the needs of people, democratize access and benefits, and are aligned with human values.
In this talk, we will share how our R&D teams in the Americas and China work side-by-side to provide rideshare experiences that are safe, convenient and affordable. We will also highlight our continuous research and work on advanced initiatives in safety and security, customer support, smart transportation systems, autonomous vehicles, and AI.
Talk 2: The Moment When the Future Fell Asleep
Recently, recurrent neural networks (RNNs) have been revolutionizing natural language processing and other fields. Among other things, RNNs can assign probabilities to sequences (such as English sentences) and transform one sequence into another (such as English into French). I will describe some of our work over the past couple of years, addressing four questions: What are neural sequence models learning? How can they learn better? Are there theoretical limits? Can they be creative?
This lecture satisfies requirements for CSCI 591: Research Colloquium.
Biography: Talk 1: Fengmin is a well-respected technologist in cybersecurity with more than 30 years experience. He is also a serial entrepreneur and angel investor. Fengmin has been a founder and senior executive in several leading security companies. Among them are Palo Alto Networks, FireEye, McAfee and Cyphort. He is a trusted advisor to many entrepreneurs and venture capitalists. He has 18 awarded patents and over 40 technical publications in security and networking.
Talk 2: Kevin Knight is Chief Scientist for Natural Language Processing (NLP) at DiDi Chuxing. He leads a DiDi lab in Marina del Rey devoted to NLP research. He is also Dean's Professor of Computer Science at USC (on leave). He received a PhD in computer science from Carnegie Mellon University and a bachelor's degree from Harvard University. Dr. Knight's research interests include human-machine communication, machine translation, language generation, automata theory, and decipherment. He has co-authored over 150 research paper on natural language processing, including best paper/demo awards at AAAI 2000, ACL 2001, NAACL 2009, ACL 2017, ACL 2018, and NAACL 2018. Dr. Knight also co-authored the widely-adopted textbook "Artificial Intelligence" (McGraw-Hill). In 2001, he co-founded Language Weaver, Inc., a machine translation company acquired by SDL plc in 2010. Dr. Knight was a key researcher in programs run by the Defense Advanced Research Projects Agency (DARPA). He served as President of the Association for Computational Linguistics (ACL) in 2011, as General Chair for the Annual Conference of the ACL in 2005, and as General Chair for the North American ACL conference in 2016. He is a Fellow of the ACL, a Fellow of ISI, and a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI).
Host: Computer Science Department
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
