Professor of Computer Science
Director, UC Santa Cruz D3 Data Science Research Center
University of California Santa Cruz
Title: The Unreasonable Effectiveness of Structure
Our ability to collect, manipulate, analyze, and act on vast amounts of data is having a profound impact on all aspects of society. Much of this data is heterogeneous in nature and interlinked in a myriad of complex ways. From information integration to scientific discovery to computational social science, we need AI methods that are able to exploit both the inherent uncertainty and the innate structure in a domain. Statistical relational learning (SRL) is a subfield that builds on principles from probability theory and statistics to address uncertainty while incorporating tools from knowledge representation and logic to represent structure. In this talk, I will give a brief introduction to SRL, present templates for common structured prediction problems, and describe modeling approaches that mix logic, probabilistic inference and latent variables. I’ll overview our recent work on probabilistic soft logic (PSL), an SRL framework for large-scale collective, probabilistic reasoning in relational domains. I’ll close by highlighting emerging opportunities (and challenges!!) in realizing the effectiveness of data and structure for knowledge discovery.
Short biography: Lise Getoor is a professor in the Computer Science Department at the University of California, Santa Cruz and a visiting researcher at MSR NYC for the fall. Her research areas include machine learning, data integration and reasoning under uncertainty, with an emphasis on graph and network data. She has over 250 publications and extensive experience with machine learning and probabilistic modeling methods for graph and network data. She is a Fellow of the Association for Artificial Intelligence, an elected board member of the International Machine Learning Society, serves on the board of the Computing Research Association (CRA), and was co-chair for ICML 2011. She is a recipient of an NSF Career Award and twelve best paper and best student paper awards. She received her PhD from Stanford University in 2001, her MS from UC Berkeley, and her BS from UC Santa Barbara, and was a professor in the Computer Science Department at the University of Maryland, College Park from 2001-2013.
Emeritus Research Director
Title: The Challenges of Integrative AI – Motivation and illustration on some planning and acting issues in robotics
Interesting scientific controversies have been going for the last few years on recent trends in AI, sometime referred to as the “swing from symbolic to numeric AI”. Such a dichotomy might not be very clarifying nor relevant for the advancement of the field. If one views and practices AI as a multidisciplinary research field whose purpose is the computational modeling and mechanization of a diversity of cognitive tasks (that may require embodiment in sensory-motor capabilities), then one has to face the challenges of integrating a diversity of mathematically heterogeneous representations. A single class of models highly adequate for, e.g., data association, can be totally ineffective for other purposes, such as, in this example, extracting and reasoning on the underlying ontology. The ambition of Integrative AI is precisely to develop approaches and architectures capable of handling heterogeneous representations.
Short biography: The research activity of Malik Ghallab is focused on robotics and AI. He contributed to topics such as object recognition and pattern matching, scene interpretation, heuristics search, unification algorithms, knowledge compiling, temporal reasoning, task planning, monitoring, and learning of robots skills and models of behaviors. He (co-)authored over 200 technical articles in journals and conference proceedings, and several textbooks and monographies. He taught AI at several universities in France and abroad as visiting professor; he advised 31 PhDs.