Lopata Hall, Room 101
Towards a New Synthesis of Reasoning and Learning
This talk discusses the role of logical reasoning in statistical machine learning. While their unification has been a long-standing and crucial open problem, automated reasoning and machine learning are still disparate fields within artificial intelligence. I will describe recent progress towards their synthesis. I start with a very practical question: how can we enforce logical constraints on the output of deep neural networks to incorporate symbolic knowledge? Second, I explain how circuits developed for tractable logical reasoning can be turned into statistical models. When brought to bear on a variety of machine learning tasks, including discrete density estimation and simple image classification, these probabilistic and logistic circuits yield state-of-the-art results.
Guy Van den Broeck is an Assistant Professor and Samueli Fellow at UCLA, in the Computer Science Department, where he directs the Statistical and Relational Artificial Intelligence (StarAI) lab. His research interests are in Machine Learning (Statistical Relational Learning, Tractable Learning, Probabilistic Programming), Knowledge Representation and Reasoning (Probabilistic Graphical Models, Lifted Probabilistic Inference, Knowledge Compilation, Probabilistic Databases), and Artificial Intelligence in general. His work has been recognized with best paper awards from key artificial intelligence venues such as UAI, ILP, KR, and AAAI (honorable mention). He also serves as Associate Editor for the Journal of Artificial Intelligence Research (JAIR). Guy is the recipient of the IJCAI-19 Computers and Thought Award.
Organizer / Host: Brendan Juba