Abstract: Belief Propagation, introduced by Judea Pearl, is a family of algorithms for computing marginal probabilities over Bayesian Networks and Markov Random Fields, and is explicitly based around concepts of message passing. In the context of Computer Vision, so-called Loopy Belief Propagation has found some success as an algorithm for stereo matching, where the entries of the output 'disparity map' operate as communicating nodes in a Markov Random Field. Concurrent ML, introduced by John Reppy, is an approach to concurrent programming based on synchronous message passing. Thus, Loopy Belief Propagation and Concurrent ML would appear to be an excellent match. No evidence of anyone attempting to meld the two in the past could be found, however. This talk will provide a brief overview of stereo matching, Loopy Belief Propagation for stereo matching, and Concurrent ML, before discussing the presenter's work so far on applying Concurrent ML to image-based tasks.

Bio: James Cooper is a Ph.D. candidate with the School of Computer Science at the University of Auckland, expecting to submit around the end of 2020/start of 2021. The focus of his dissertation is on investigating the efficacy of parallel Concurrent ML programming for implementing stereo vision algorithms that are theoretically based on message passing. His main research interests are in applied functional and parallel programming (and programming languages generally), image processing & computer vision, and membrane computing. His ORCID is https://orcid.org/0000-0001-9954-3280. What little free time he has is usually spent reading textbooks, watching quiz shows, or playing table-top roleplaying games.

P.S. We will likely go to [late] lunch at M&H at 2pm afterwards, please email Alex Potanin if you want to join us (alex.potanin@vuw.ac.nz).