Select a calendar:
Filter February Events by Event Type:
SUNMONTUEWEDTHUFRISAT
Events for February 27, 2017
-
CS Colloquium: Ellie Pavlick (University of Pennsylvania) - Natural Language Understanding with Paraphrases and Composition
Mon, Feb 27, 2017 @ 11:00 AM - 12:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Ellie Pavlick, University of Pennsylvania
Talk Title: Natural Language Understanding with Paraphrases and Composition
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
Natural language processing (NLP) aims to teach computers to understand human language. NLP has enabled some of the most visible applications of artificial intelligence, including Google search, IBM Watson, and Apple's Siri. As AI is applied to increasingly complex domains such as health care, education, and government, NLP will play a crucial role in allowing computational systems to access the vast amount of human knowledge documented in the form of unstructured speech and text.
In this talk, I will discuss my work on training computers to make inferences about what is true or false based on information expressed in natural language. My approach combines machine learning with insights from formal linguistics in order to build data-driven models of semantics which are more precise and interpretable than would be possible using linguistically naive approaches. I will begin with my work on automatically adding semantic annotations to the 100 million phrase pairs in the Paraphrase Database (PPDB). These annotations provide the type of information necessary for carrying out precise inferences in natural language, transforming the database into a largest available lexical semantics resource for natural language processing. I will then turn to the problem of compositional entailment, and present an algorithm for performing inferences about long phrases which are unlikely to have been observed in data. Finally, I will discuss my current work on pragmatic reasoning: when and how humans derive meaning from a sentence beyond what is literally contained in the words. I will describe the difficulties that such "common-sense" inference poses for automatic language understanding, and present my on-going work on models for overcoming these challenges.
Biography: Ellie Pavlick is a PhD student at the University of Pennsylvania, advised by Dr. Chris Callison-Burch. Her dissertation focuses on natural language inference and entailment. Outside of her dissertation research, Ellie has published work on stylistic variation in paraphrase--e.g. how paraphrases can effect the formality or the complexity of language--and on applications of crowdsourcing to natural language processing and social science problems. She has been involved in the design and instruction of Penn's first undergraduate course on Crowdsourcing and Human Computation (NETS 213). Ellie is a 2016 Facebook PhD Fellow, and has interned at Google Research, Yahoo Labs, and the Allen Institute for Artificial Intelligence.
Host: CS Department
Location: Ronald Tutor Hall of Engineering (RTH) - 217
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
Navigating the the U.S. Recruitment Process -VIRTUAL WORKSHOP
Mon, Feb 27, 2017 @ 12:00 PM - 01:00 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
This workshop will provide students tips on how to navigate the process of U.S. corporate recruiting and will touch on American culture norms.
To join the workshop, go to https://bluejeans.com/746143734 at the workshop start time and login with your USC netID and password.Location: VIRTUAL WORKSHOP
Audiences: All Viterbi Students
Contact: RTH 218 Viterbi Career Connections
-
Seminars in Biomedical Engineering
Mon, Feb 27, 2017 @ 12:30 PM - 01:50 PM
Alfred E. Mann Department of Biomedical Engineering
Conferences, Lectures, & Seminars
Speaker: Mahnaz Shahidi, PhD, Professor of Ophthalmology and Biomedical Engineering Riffenburgh Professor in Glaucoma Vice Chair for Translational Research Department of Ophthalmology University of Southern California
Talk Title: Multimodal Imaging of Retinal Oxygen Delivery and Metabolism
Abstract: Retinal tissue function can be adversely affected by inadequate delivery and/or consumption of oxygen. In fact, derangements in retinal oxygenation are thought to contribute significantly to the development of common vision threatening retinal diseases. However, mechanisms that implicate oxygen in the development of retinal pathologies and impairment of retinal function are not completely understood. Therefore, technologies that allow assessment of oxygen tension in the retinal vasculature and tissue are needed to broaden knowledge of disease pathophysiology, and thereby advance diagnostic and therapeutic procedures. We have developed an optical section phosphorescence lifetime imaging technique that allows depth-resolved mapping of retinal vascular oxygen tension and measurement of inner retinal oxygen extraction fraction. Combined with fluorescent microsphere imaging for measurement of retinal blood flow, oxygen delivery by the retinal circulation and global inner retinal oxygen metabolism are derived. These technologies have been applied for assessment of retinal oxygen delivery and metabolism in experimental animal models of retinal ischemia.
Host: Qifa Zhou
Location: Olin Hall of Engineering (OHE) - 122
Audiences: Everyone Is Invited
Contact: Mischalgrace Diasanta
-
Center for Cyber-Physical Systems and Internet of Things and Ming Hsieh Institute for Electrical Engineering Joint Seminar Series on Cyber-Physical Systems
Mon, Feb 27, 2017 @ 02:00 PM - 03:30 PM
Ming Hsieh Department of Electrical and Computer Engineering
Conferences, Lectures, & Seminars
Speaker: Geir E. Dullerud, Professor, University of Illinois at Urbana-Champaign
Talk Title: Statistical Validation and Principle-Based Simulation of Complex Cyber-Controlled Systems
Abstract: The talk will focus on simulation and a computational approach to verification of the hybrid mathematical models that are formed when combining physics-based models with discrete-transition models, such as those which model software algorithms. Namely, the mathematical models that arise when for instance considering Cyberphysical Systems, or the Internet of Things.
In many game theory and filtering problems it is not possible to analytically obtain solutions for statistical properties of systems under study, and in the first part of the talk we will describe our recent work on numerical approaches to obtaining estimates of these properties, and the application of the techniques developed to particle filtering. Monte Carlo simulation of Markov processes allows the numerical estimation of their statistical properties from an ensemble of sample system paths. We present methods for generating reduced-variance path ensembles for the tau-leaping discrete-time simulation algorithm, which allows mean stochastic process dynamics to be estimated with substantially smaller ensemble sizes. Our methods are based on antithetic and stratified sampling of Poisson random variates, and we provide a combination of analytical proofs and numerical evidence for their performance, which can frequently be a 2-3 orders of magnitude improvement over standard Monte Carlo. Application examples will be discussed.
The second part of the talk will concentrate on system verification, and will present a new verification algorithm for continuous-time stochastic hybrid systems, whose specifications are expressed in metric interval temporal logic (MITL), by deploying a novel model reduction method. By partitioning the state space of the hybrid system and computing the optimal transition rates between partitions, we provide a procedure to both reduce the system to a continuous-time Markov chain, and the associated specification formulas. We prove that the unreduced formulas hold (or do not) if the corresponding reduced formula on the Markov chain is robustly true (or false) under certain perturbations. In addition, a stochastic algorithm to complete the verification has been developed. We have extended the approach of this algorithm, and have developed a direct stochastic algorithm for probabilistically verifying a certain hybrid system class, and applied this technique to an extensive benchmark problem with realistic dynamics.
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 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).
Host: Paul Bogdan
Location: Hughes Aircraft Electrical Engineering Center (EEB) - 132
Audiences: Everyone Is Invited
Contact: Estela Lopez
-
CAIS Seminar Series: Dr. Pascal Van Hentenryck (University of Michigan) - The Case of Infrastructure Optimization
Mon, Feb 27, 2017 @ 04:00 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Pascal Van Hentenryck, University of Michigan
Talk Title: The Case of Infrastructure Optimization
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Computer Science Research Colloquium.
In the last decade, massive amount of information has been collected about critical infrastructures, including the transportation network and the electrical power system. These data sets, together with progress in Artificial Intelligence and Operations Research, make it possible to analyze, predict, and optimize these infrastructures with unprecedented fidelity. This talk demonstrates the societal benefits of this transformation on a number of case studies in evacuation planning, public transportation, and power restoration.
Biography: Dr. Pascal Van Hentenryck is the Seth Bonder Collegiate Professor of Engineering at the University of Michigan. He is Professor of Industrial and Operations Engineering, Professor of Electrical Engineering and Computer Science, and core faculty in the Michigan Institute of Data Science. He is the author of the pioneering CHIP and OPL optimization systems, which have been widely used in academia and industry. Dr. Van Hentenryck is the author of five MIT Press books and is a fellow of AAAI and INFORMS.
Host: Milind Tambe
Location: John Stauffer Science Lecture Hall (SLH) - 100
Audiences: Everyone Is Invited
Contact: Assistant to CS chair
-
NAVAIR Information Session
Mon, Feb 27, 2017 @ 05:30 PM - 06:30 PM
Viterbi School of Engineering Career Connections
Workshops & Infosessions
NAVAIR Overview - Overview of NAVAIR and discussion of employment opportunities as a civilian employee of the Department of the Navy
Location: Seeley G. Mudd Building (SGM) - 101
Audiences: All Viterbi Students
Contact: RTH 218 Viterbi Career Connections
