FLAIRS-31‎ > ‎

Keynote Speakers

Dr. Rina DechterDonald Bren School of Information and Computer Sciences, UC Irvine
Rina Dechter’s research centers on computational aspects of automated reasoning and knowledge representation including search, constraint processing, and probabilistic reasoning. She is a Chancellor's Professor of Computer Science at the University of California, Irvine. She holds a Ph.D. from UCLA, an M.S. degree in applied mathematics from the Weizmann Institute, and a B.S. in mathematics and statistics from the Hebrew University in Jerusalem. She is an author of Constraint Processing published by Morgan Kaufmann (2003), and Reasoning with Probabilistic and Deterministic Graphical Models: Exact Algorithms by Morgan and Claypool publishers, 2013, has co-authored close to 200 research papers, and has served on the editorial boards of: Artificial Intelligence, the Constraint Journal, Journal of Artificial Intelligence Research (JAIR), and Journal of Machine Learning Research (JMLR). She is a Fellow of the American Association of Artificial Intelligence 1994, was a Radcliffe Fellow 2005–2006, received the 2007 Association of Constraint Programming (ACP) Research Excellence Award, and she is a 2013 ACM Fellow. She has been Co-Editor- in-Chief of Artificial Intelligence since 2011. She is also co-editor with Hector Geffner and Joe Halpern of the book Heuristics, Probability and Causality: A Tribute to Judea Pearl, College Publications, 2010.

Abstract: Probabilistic Reasoning Meets Heuristic Search

Graphical models, including constraint networks, Bayesian networks, Markov random fields and influence diagrams, have become a central paradigm for knowledge representation and reasoning in Artificial Intelligence, and provide powerful tools for solving problems in a variety of application domains, including coding and information theory, signal and image processing, data mining, learning, computational biology, and computer vision. Although past decades have seen considerable progress in algorithms in graphical models, many real-world problems are of such size and complexity that they remain out of reach. Advances in exact and approximate inference methods are thus crucial to address these important problems with potential impact across many computational disciplines. Exact inference is typically NP-hard, motivating the development of approximate and anytime techniques. 

Existing algorithms typically take one of two approaches: Inference, expressed as message-passing schemes, or search and conditioning methods. In the past decade, my research group at UCI has developed state-of-the art algorithms based on combining heuristic search with variational-based message passing approximations, winning a few solver competitions.

In this talk she reviews the main principles behind the AND/OR search and show how it can be  guided by heuristics based on variational inference (e.g., decomposition bounds such as weighted mini-bucket and cost-shifting schemes) for solving probabilistic and deterministic graphical models queries such as satisfiability, optimization (e.g., MAP), weighted counting (e.g., probability of evidence) and their combinations (e.g., maximizing expected utility) that allow flexible trading of memory for time and time for accuracy. Emerging solvers aim for anytime behavior that generates not only an approximation that improves with time, but also upper and lower bounds which become tighter with more time.
 Dr. Raymond Mooney, Professor in the Department of Computer Science at the University of Texas at Austin
Raymond J. Mooney is a Professor in the Department of Computer Science at the University of Texas at Austin. He received his Ph.D. in 1988 from the University of Illinois at Urbana/Champaign. He is an author of over 160 published research papers, primarily in the areas of machine learning and natural language processing. He was the President of the International Machine Learning Society from 2008-2011, program co-chair for AAAI 2006, general chair for HLT-EMNLP 2005, and co-chair for ICML 1990. He is a Fellow of the American Association for Artificial Intelligence, the Association for Computing Machinery, and the Association for Computational Linguistics and the recipient of best paper awards from AAAI-96, KDD-04, ICML-05 and ACL-07.

Abstract:  Robots that Learn Grounded Language Through Interactive Dialog

In order to develop an office robot that learns to accept natural language commands, we have developed methods that learn from natural dialog with ordinary users rather than from manually labeled data.  By engaging users in dialog, the system learns a semantic parser, an effective dialog management policy, and a grounded semantic lexicon that connects words to multi-modal (visual, auditory and haptic) perception. In addition to learning from clarification dialogs when understanding user commands, it also engages people in interactive games such as "I Spy." We have tested our approach on both simulated robots using on-line crowdsourced users on the web as well as with people interacting with real robots in our lab. Experimental results demonstrate our methods  produce more successful, shorter dialogs over time and learn to accurately identify objects from natural language descriptions using multi-modal perception.
Dr. Peter WurmanVice-President of Engineering at Cogitai

Pete Wurman is currently VP of Engineering at Cogitai, a startup in the space of machine learning. Prior to Cogitai, Pete was a Co-founder and CTO of Kiva Systems, the Boston-based company that pioneered the use of mobile robotics in warehouses and distribution facilities. In May of 2012, Kiva was acquired by Amazon.com < Caution-http://Amazon.com > , which has now deployed tens of thousands of Kiva robots into its warehouses.

Prior to joining Kiva, Pete was an Associate Professor of Computer Science at North Carolina State University in Raleigh, NC.  Pete’s teaching focus was e-commerce systems, and his research focused on electronic auctions (especially combinatorial auctions), multi-agent systems, and resource allocation. 

Abstract: How Kiva Robots Disrupted Warehousing

Kiva Systems introduced swarms of agile robots into an industry dominated by stationary conveyor systems. The path from concept through successful startup and eventual acquisition involved challenges on all fronts. In this talk I’ll explain the business problem that motivated the innovation, Kiva technology and the benefits it brought to customers, and the future of applications of robotics in warehouses.