Seminars and Events

Artificial Intelligence Seminar

Probabilistic Reasoning about Plants, Animals, Objects, and People: a Story of Romance and Disappointment.

Event Details

The first part of the title is from Pinker [1997]  “The mind is a neural computer, fitted by natural selection with combinatorial algorithms for causal and probabilistic reasoning about plants, animals, objects, and people.” Over the decades researchers have fallen in love with many technologies for learning reasoning about entities and relations under uncertainty, from probabilistic logic programs to Markov logic to knowledge graphs to embedding-based models to graph neural networks. Unfortunately, none of them are the silver bullet we had hoped for. The elephant in the room is data: what it means, where it comes from, what to do with only positive data, and how to evaluate predictions, and the different ways in which we can be uncertain. In this talk, I will talk about what each of these technologies is good for and why it isn’t, by itself, the solution.

Speaker Bio

David Poole is a Professor of Computer Science at the University of British Columbia. He is known for his work on combining logic and probability,  probabilistic inference,  relational probabilistic models, statistical relational AI  and semantic science. He is a co-author of two AI textbooks (Cambridge University Press, 2010, 2nd edition 2017 and Oxford University Press, 1998), and coauthor of " Statistical Relational Artificial Intelligence: Logic, Probability, and Computation", (Morgan & Claypool 2016),  and co-editor of a forthcoming book "Introduction to Lifted Inference"  (MIT Press 2021).  He is a former chair of the Association for Uncertainty in Artificial Intelligence, the winner of the Canadian AI Association (CAIAC) 2013 Lifetime Achievement Award,  and is a Fellow of the Association for the Advancement Artificial Intelligence (AAAI) and CAIAC.  See http://www.cs.ubc.ca/~poole/publications.html for a list of his publications.