Hackerman B17 @ 3400 N Charles St, Baltimore, MD 21218, USA
Many AI tasks are best performed by machine learning approaches. Recently, progress in ML has been greatly accelerated byhigh-performance, easily programmable tools for defining and optimizing deep neural-network architectures. However, intelligence requires, among many other abilities, the ability to perform logical reasoning, and itis not obvious how to best combine logical reasoning with neural systems. In this talk, I will discuss a system that can scalably perform non-trivial symbolic logical reasoning in a way that allows for tight integrationwith neural learning methods.
The system I will describe, TensorLog,is a carefully restricted probabilistic first-order logic in which inference can be compiled to differentiable functions in a neural network infrastructure, such as Tensorflow. This enables one to use high-performance deep learning frameworks to learn parameters of a probabilistic logic. TensorLog has been used for several diverse tasks, including semi-supervised learning for network data (using logic constraints on classifiers), question-answering against a KB, and relational learning.
William Cohen is a Director of Research & Engineering at Google AI, and is based in Google’s Pittsburgh office. He received his bachelor’s degree in Computer Science from Duke University in 1984, and a PhD in Computer Science from Rutgers University in 1990. From 1990 to 2000 Dr. Cohen worked at AT&T Bell Labs and later AT&T Labs-Research, and from April 2000 to May 2002 Dr. Cohen worked at Whizbang Labs, a company specializing in extracting information from the web. From 2002 to 2018, Dr. Cohen worked at Carnegie Mellon University in the Machine Learning Department, with a joint appointment in the Language Technology Institute, as an Associate Research Professor, a Research Professor, and a Professor. Dr. Cohen also was theDirector of the Undergraduate Minor in Machine Learning at CMU and co-Director of the Master of Science in ML Program.Dr. Cohen is a past presidentof the International Machine Learning Society. In the past he has also served as an action editor for the the AI and Machine Learning series of books published by Morgan Claypool, for the journal Machine Learning, the journal Artificial Intelligence, the Journal of Machine Learning Research, and the Journal of Artificial Intelligence Research. He was General Chair for the 2008 International Machine Learning Conference, held July 6-9 at the University of Helsinki, in Finland; Program Co-Chair of the 2006 International Machine Learning Conference; and Co-Chair of the 1994 International Machine Learning Conference. Dr. Cohen was also the co-Chair for the 3rd Int’l AAAI Conference on Weblogs and Social Media, which was held May 17-20, 2009 in San Jose, and was the co-Program Chair for the 4rd Int’l AAAI Conference on Weblogs and Social Media. He is a AAAI Fellow, andwas a winner of the 2008 the SIGMOD ?Test of Time? Award for the most influential SIGMOD paper of 1998, and the 2014 SIGIR ?Test of Time? Award for the most influential SIGIR paper of 2002-2004.
Dr. Cohen’s research interests include information integration and machine learning, particularly information extraction, text categorization and learning from large datasets. He has a long-standing interest in statistical relational learning and learning models, or learning from data, that display non-trivial structure. He holds seven patents related to learning, discovery, information retrieval, and data integration, and is the author of more than 200 publications.
Dr. Cohen is currently on leave from his position as a Professor in the Department of Machine Learning, with a joint appointment in the Language Technology Institute.