Skip to content

Dr. Pedro Domingos – The Spring 2015 Distinguished Lecture Series

The first talk in the Computer Science Department’s spring 2015 Distinguished Lecture Series took place on February 27th 2015 and featured Dr. Pedro Domingos. He is currently a professor of Computer Science and Engineering at the University of Washington. His research interests are in machine learning, artificial intelligence and data science. He received a PhD in Information and Computer Science from the University of California at Irvine, and is the author or co-author of over 200 technical publications.

The talk was titled “Sum-Product Networks: Deep Models with Tractable Inference.” During his talk, Dr. Domingos, discussed big data and how in principle learning is possible within probabilistic models, but that inference in these models is prohibitively expensive. Since inference is typically a subroutine of learning, in practice learning such models is very difficult. Sum-product networks (SPNs) are a new model class that squares this circle by providing maximum flexibility while guaranteeing tractability. In contrast to Bayesian networks and Markov random fields, SPNs can remain tractable even in the absence of conditional independence. SPNs are defined recursively: an SPN is a univariate distribution, a product of SPNs over disjoint variables, or a weighted sum of SPNs over the same variables. The partition function, all marginal and all conditional MAP states of an SPN can be computed in time, linear in its size. SPNs have most tractable distributions as special cases, including hierarchical mixture models, thin junction trees, and non-recursive probabilistic context-free grammars. Dr. Domingos presented generative and discriminative algorithms for learning SPN weights, and an algorithm for learning SPN structure. SPNs have achieved impressive results in a wide variety of domains, including object recognition, image completion, collaborative filtering, and click prediction. The algorithms can easily learn SPNs with many layers of latent variables, making them arguably the most powerful type of deep learning to date, according to Dr. Domingos.

Dr. Domingos is a Fellow of the Association for the Advancement of Artificial Intelligence (AAAI). He has received a Sloan Fellowship, a National Science Foundation (NSF) Faculty Early Career Development (CAREER) Award, a Fulbright Scholarship, and an International Business Machines (IBM) Faculty Award. He also has best paper awards at several leading conferences including the International Conference on Knowledge Discovery and Data Mining (KDD-98 and KDD-99), as well as the European Conference on Principles and Practice of Knowledge Discovery in Databases (PKDD) in 2005.

He is a member of the editorial board of the Machine Learning journal, co-founder of the International Machine Learning Society (IMLS), and past associate editor of Journal of Artificial Intelligence Research (JAIR). Dr. Domingos was a program co-chair of the International Conference on Knowledge Discovery and Data Mining in 2003 (KDD) and Statistical Learning Research (SLR) in 2009, and has served on numerous program committees.

 

 

To view Dr. Pedro Domingos’ website, please Click Here.

NSF Projects Offer Research Experience for Undergraduates
Computer Science Students Earn Top Awards