Select a calendar:
Filter November Events by Event Type:
Conferences, Lectures, & Seminars
Events for November
-
CAIS Seminar: Dr. Lucas Joppa (Microsoft Research) - AI for Earth
Thu, Nov 02, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Lucas Joppa, Microsoft Research
Talk Title: AI for Earth
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Time is too short, and resources too thin, to find solutions to our environmental sustainability challenges without the exponential power and assistance of AI. This talk will cover AI's transformative potential for both closing critical information gaps on Earth's natural environments and optimizing our management of them.
Biography: Dr. Lucas Joppa is the Chief Environmental Scientist at Microsoft Research and leads the company's AI for Earth program, an initiative dedicated to leveraging the latest advances in AI research and engineering for solutions in the four key areas of agriculture, climate, water, and biodiversity conservation.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Danqi Chen (Stanford) - From Reading Comprehension to Open-Domain Question Answering
Tue, Nov 07, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Danqi Chen, Stanford
Talk Title: From Reading Comprehension to Open-Domain Question Answering
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Enabling a computer to understand a document so that it can answer comprehension questions is a central, yet unsolved, goal of NLP. This task of reading comprehension (i.e., question answering over a passage of text) has received a resurgence of interest, due to the creation of large-scale datasets and well-designed neural network models.
I will talk about how we build simple and effective models for advancing a machine's ability at reading comprehension. I'll focus on explaining the logical structure behind these neural architectures and discussing the capacities of these models as well as their limits.
Next I'll talk about how we combine state-of-the-art reading comprehension systems with traditional IR components to build a new generation of open-domain question answering systems. Our system is much simpler than traditional QA systems and able to answer questions efficiently over the full English Wikipedia and shows great promise on multiple QA benchmarks.
Biography: Danqi Chen is a Ph.D. candidate in Computer Science at Stanford University, advised by Christopher Manning. She works on deep learning for natural language processing, and is particularly interested in the intersection between text understanding and knowledge representation/reasoning. Her research spans from machine comprehension/question answering to knowledge base construction and syntactic parsing, with an emphasis on building principled yet highly effective models. She is a recipient of a Facebook Fellowship, a Microsoft Research Women's Fellowship and outstanding paper awards at ACL'16 and EMNLP'17. Previously, she received her B.S. with honors from Tsinghua University in 2012.
Host: Fei Sha
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Li Xiong (Emory University) - Privacy-Preserving Data Sharing and Analytics with Differential Privacy
Thu, Nov 09, 2017 @ 01:30 PM - 02:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Li Xiong, Emory University
Talk Title: Privacy-Preserving Data Sharing and Analytics with Differential Privacy
Abstract: While Big Data promises significant value, it also raises increasing privacy concerns. In this talk, I will describe our efforts towards a comprehensive privacy-preserving data sharing and analytics framework. Following an overview of the framework, we discuss two settings based on state-of-the-art differential privacy techniques: 1) aggregated data sharing for data mining and analytics, and 2) individual location sharing for location based services. For aggregated sharing, I will present several technical solutions for handing different types of data including sequential and time series data, using medical and spatiotemporal data mining applications. For individual data sharing, I will present our approach towards a rigorous and customizable privacy notion extending the differential privacy framework for location protection, with location based applications such as nearest POI search and geospatial crowdsourcing.
This lecture satisfies requirements for CSCI 591: Research Colloquium. Please note, due to limited capacity in SOS B2, seats will be first come first serve.
Biography: Li Xiong is Professor of Computer Science and Biomedical Informatics at Emory University and holds a Winship Distinguished Research Professorship. She has a PhD from Georgia Institute of Technology, an MS from Johns Hopkins University, and a BS from University of Science and Technology of China, all in Computer Science. She and her research group, Assured Information Management and Sharing (AIMS), conduct research that addresses both fundamental and applied questions at the interface of data privacy and security, spatiotemporal data management, and health informatics. She has published over 100 papers in premier journals and conferences including TKDE, JAMIA, VLDB, ICDE, CCS, and WWW, and has received four best paper awards. She currently serves as associate editor for IEEE Transactions on Knowledge and Data Engineering (TKDE) and on numerous program committees for data management and data security conferences. She is a recipient of a Google Research Award, IBM Smarter Healthcare Faculty Innovation Award, Cisco Research Award, and Woodrow Wilson Fellowship. Her research is supported by NSF (National Science Foundation), NIH (National Institute of Health), AFOSR (Air Force Office of Scientific Research), and PCORI (Patient-Centered Outcomes Research Institute).
Host: Muhammad Naveed
Location: Social Sciences Building (SOS) - B2
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Jimmy Ba (University of Toronto) - Progress and Challenges in Training Neural Networks
Thu, Nov 09, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Jimmy Ba, University of Toronto
Talk Title: Progress and Challenges in Training Neural Networks
Series: Visa Research Machine Learning Seminar Series hosted by USC Machine Learning Center
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Optimization lies at the core of any deep learning systems. In this talk, I will first discuss the recent advances in optimization algorithms to train deep learning models. Then I will present a novel family of 2nd-order optimization algorithms that leverage distributed computing to significantly shortening the training time of neural networks with tens of millions of parameters. The talk will conclude by showing how our algorithms can be successfully applied to domains such as reinforcement learning and generative adversarial networks.
Biography: Jimmy is finishing his PhD with Geoff Hinton in the Machine Learning group at the University of Toronto. Jimmy will be a Computational Fellow at MIT before returning as full-time faculty to the CS department at UofT, as well as joining the Vector Institute. Jimmy completed his BAc, MSc at UofT working with Brendan Frey and Ruslan Salakhutdinov. He has previously spent time at Google Deepmind and Microsoft Research, and is a recipient of Facebook Graduate Fellowship for 2016 in machine learning. His primary research interests are in the areas of artificial intelligence, neural networks, and numerical optimization.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Dr. John Clapp (University of Southern California) - A Systems Dynamic Approach to Understanding Heavy Drinking Events: Measures, Methods and Models
Thu, Nov 09, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. John Clapp, University of Southern California
Talk Title: A Systems Dynamic Approach to Understanding Heavy Drinking Events: Measures, Methods and Models
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: Dr. Clapp will discuss a collaborative modeling effort among a team of engineers and social scientists to better understand the complex dynamics underlying heavy drinking at the event level. The goal of this ongoing effort is to develop invivo smart interventions aimed at changing problematic drinking trajectories to prevent event level problems including alcohol poisoning, drunk driving, and sexual assault. His presentation will cover the collaborative modeling effort, computation models, and validation measures and methods. The current state of the models and next steps will be discussed.
Biography: Dr. Clapp is Executive Vice Dean and Professor in the Suzanne Dworak-Peck School of Social Work. His work has focused largely on the etiology and prevention of acute alcohol-related problems.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
MASCLE Machine Learning Seminar: Robert Schapire (Microsoft Research NYC) - The Contextual Bandits Problem: Techniques for Learning to Make High-Reward Decisions
Tue, Nov 14, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Robert Schapire, Microsoft Research NYC
Talk Title: The Contextual Bandits Problem: Techniques for Learning to Make High-Reward Decisions
Series: NVIDIA Distinguished Lecture Series in Machine Learning
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
We consider how to learn through experience to make intelligent decisions. In the generic setting, called the contextual bandits problem, the learner must repeatedly decide which action to take in response to an observed context, and is then permitted to observe the received reward, but only for the chosen action. The goal is to learn to behave nearly as well as the best policy (or decision rule) in some possibly very large and rich space of candidate policies. This talk will describe progress on developing general methods for this problem and some of its variants.
Biography: Robert Schapire is a Principal Researcher at Microsoft Research in New York City. He received his PhD from MIT in 1991. After a short post-doc at Harvard, he joined the technical staff at AT&T Labs (formerly AT&T Bell Laboratories) in 1991. In 2002, he became a Professor of Computer Science at Princeton University. He joined Microsoft Research in 2014. His awards include the 1991 ACM Doctoral Dissertation Award, the 2003 Gödel Prize, and the 2004 Kanelakkis Theory and Practice Award (both of the last two with Yoav Freund). He is a fellow of the AAAI, and a member of both the National Academy of Engineering and the National Academy of Sciences. His main research interest is in theoretical and applied machine learning, with particular focus on boosting, online learning, game theory, and maximum entropy.
Host: Haipeng Luo
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Dr. Brian Milch (Google) - Combining Probabilistic and Neural Approaches for Text Classification
Tue, Nov 14, 2017 @ 05:00 PM - 06:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. Brian Milch, Google
Talk Title: Combining Probabilistic and Neural Approaches for Text Classification
Series: CS Colloquium
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
In the Semantic Signals group at Google Los Angeles, we build classifiers that label text with hundreds of human-defined categories across dozens of languages. Labeled training data is sparse, so we've found it essential to incorporate unsupervised learning methods that take advantage of unlabeled text. One of our tools is a probabilistic topic model that learns discrete "clusters" to explain word co-occurrence patterns in a large corpus, and then identifies the clusters that best explain a new document. Another tool is a neural net that learns embeddings of individual words in a continuous space. I'll discuss how these approaches play complementary roles in our text classification pipeline.
Biography: Brian Milch is a software engineer at Google's Los Angeles office. He received a B.S. in Symbolic Systems from Stanford University in 2000, and a Ph.D. in Computer Science from U.C. Berkeley in 2006. He then spent two years as a post-doctoral researcher at MIT before joining Google in 2008. He has contributed to Google production systems for spelling correction, transliteration, and semantic modeling of text.
Host: Fei Sha
Location: Seeley G. Mudd Building (SGM) - 124
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CAIS Seminar: Dr. David Morton (Northwestern University) - Using Optimization to Thwart Viruses
Thu, Nov 16, 2017 @ 04:00 PM - 05:00 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Dr. David Morton, Northwestern University
Talk Title: Using Optimization to Thwart Viruses
Series: Center for AI in Society (CAIS) Seminar Series
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium
We describe the use of data-driven optimization models to inform resource allocation to help detect or mitigate the spread of a virus. One set of models guide preparation for, and response to, an influenza pandemic. In particular, we optimize: the mix of central and regional stockpiles of ventilators, accounting for stochastic peak-week demand; the spatial allocation of antivirals, considering under-insured populations and hard-to-reach locations; and, the spatial allocation of multiple types of vaccines with differing suitability for each prioritized target population. In addition, we discuss rapidly detecting the spread of a cell-phone virus on a contact network of handsets.
Biography: David Morton is the David A. and Karen Richards Sachs Professor and Chair of Industrial Engineering and Management Sciences at Northwestern University. His research interests include stochastic and large-scale optimization with applications in security, public health, and energy systems. Prior to joining Northwestern, he was on the faculty at the University of Texas at Austin, worked as a Fulbright Research Scholar at Charles University in Prague, and was a National Research Council Postdoctoral Fellow in the Operations Research Department at the Naval Postgraduate School.
Host: Milind Tambe
Location: Seeley Wintersmith Mudd Memorial Hall (of Philosophy) (MHP) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
MASCLE Machine Learning Seminar: Carl Vondrick (Google) - Predictive Vision
Tue, Nov 28, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Carl Vondrick, Google
Talk Title: Predictive Vision
Series: Visa Research Machine Learning Seminar Series hosted by USC Machine Learning Center
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Machine learning is revolutionizing our world: computers can recognize images, translate language, and even play games competitively with humans. However, there is a missing piece that is necessary for computers to take actions in the real world. My research studies Predictive Vision with the goal of anticipating the future events that may happen. To tackle this challenge, I present predictive vision algorithms that learn directly from large amounts of raw, unlabeled data. Capitalizing on millions of natural videos, my work develops methods for machines to learn to anticipate the visual future, forecast human actions, and recognize ambient sounds.
Biography: Carl Vondrick is a research scientist at Google and he will be an assistant professor at Columbia University in fall 2018. He received his PhD from the Massachusetts Institute of Technology in 2017. His research was awarded the Google PhD Fellowship, the NSF Graduate Fellowship, and is featured in popular press, such as NPR, CNN, the Associated Press, and the Late Show with Stephen Colbert.
Host: Yan Liu
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Andrew Miller (Harvard) - Advances in Monte Carlo Variational Inference
Thu, Nov 30, 2017 @ 02:00 PM - 03:20 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Andrew Miller, Harvard
Talk Title: Advances in Monte Carlo Variational Inference
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
Probabilistic modeling is a natural framework for reasoning about noisy data. Well-constructed probabilistic models that combine prior knowledge with data can uncover latent structure, make predictions, and support scientific discovery. However, specifying a model and actually applying a model to data are two distinct challenges. In this talk, I will illustrate and address these challenges by presenting new models and inference methods. Monte Carlo variational inference (MCVI) is an optimization-based class of approximate inference algorithms applicable to a wide range of probabilistic models. I will present work that improves MCVI by increasing the expressiveness of approximations and the robustness of optimization. I will also present new probabilistic models developed for a variety of applied problems.
Biography: Andy Miller is a PhD candidate in computer science at Harvard University, studying statistical machine learning. He develops probabilistic models and inference methods for complex, high-dimensional data in applications ranging from astronomy to health care to sports analytics. He is currently in the final year of his program, advised by Ryan Adams (Princeton and Google Brain), Finale Doshi-Velez (Harvard), and Luke Bornn (Simon Fraser).
Host: Fei Sha
Location: Seeley G. Mudd Building (SGM) - 123
Audiences: Everyone Is Invited
Contact: Computer Science Department
-
CS Colloquium: Zi Wang (MIT) - Bayesian Optimization and How to Scale it Up
Thu, Nov 30, 2017 @ 03:30 PM - 04:50 PM
Thomas Lord Department of Computer Science
Conferences, Lectures, & Seminars
Speaker: Zi Wang, MIT
Talk Title: Bayesian Optimization and How to Scale it Up
Abstract: This lecture satisfies requirements for CSCI 591: Research Colloquium.
In recent years, Bayesian optimization (BO) has become a popular and effective approach to optimize an expensive black-box function with assumptions usually expressed by a Gaussian process prior. Successful applications include tuning hyper-parameters for neural networks, optimizing control parameters for robots, and designing biological experiments. Despite these successes, BO has been limited to small-scale and low-dimensional problems due to computational challenges with Gaussian processes and statistical challenges in high-dimensional settings. In this talk, I will present our recent work on scaling up BO from several aspects. First, I will introduce Max-value Entropy Search, a new BO strategy that improves sample-efficiency and obtains the first regret bound for a variant of the entropy search methods. Building on the new acquisition function, we extend our approach to high dimensions by learning the additive structures of the kernel. And finally, we propose a scalable high-dimensional BO approach that gives previously impossible results of scaling up BO to tens of thousands of observations within minutes of computation. We also show some interesting new findings on how evolutionary algorithms and BO are related, and establish novel connections among several well-known BO methods including entropy search, GP-UCB, and probability of improvement.
Biography: Zi Wang is a Ph.D. student at the MIT Computer Science and Artificial Intelligence Laboratory, advised by Stefanie Jegelka, Leslie Kaelbling and Tomás Lozano-Pérez. She received her S.M. in Electrical Engineering and Computer Science from MIT in Feb. 2016, and B.Eng. in Computer Science and Technology from Tsinghua University in Jul. 2014. Her research interests lie broadly in machine learning and artificial intelligence, currently with applications to robotics problems.
Host: Fei Sha
Location: Henry Salvatori Computer Science Center (SAL) - 101
Audiences: Everyone Is Invited
Contact: Computer Science Department