Slides Available

image001Clark Glymour, PhD, Alumni University Professor of Philosophy, Carnegie Mellon University, will deliver the Distinguished Lecture in Causal Discovery, “Computational Causal Discovery,” at 11:00 am on Thursday, February 26, 2015, in Rooms 407A/B BAUM, 5607 Baum Blvd., The Offices at Baum.

Abstract: Thirty years ago, the very idea that computers could be used to discover causal information buried in large collections of observations was widely ridiculed as absurd. Between then and now something happened to change much of that opinion. Dr. Glymour will talk about the changes in our understanding of how causal relations and probabilities relate to one another, and how those changes made computerized search possible, with some examples. Dr. Glymour will also talk about the aims of the Center for Causal Discovery, and what progress has been made in the four months since its inception.

Biography:  Dr. Glymour’s current research applies previous work on causal Bayes nets and formal learning theory to a variety of topics. With Joseph Ramsey and with collaborators at NASA Ames he has worked on automated identification of mineral composition from spectra. With the Computational Systems Biology Group, he has worked on the possibilities and limitations of machine learning procedures for inferring gene regulation from measurements of messenger RNA concentrations. In collaboration with several psychologists and with his former student, David Danks, he has also worked on mathematical aspects of the psychology of causal reasoning, work that he has summarized in The Mind’s Arrows: Bayes Nets and Graphical Causal Models in Psychology (MIT, 2003). He has worked on learning algorithms for distributed datasets with distinct but not disjoint variable sets, learning classifiers for data with few cases and very large numbers of variables, forecasting rare events, particularly forest fires, and the causal analysis of climate teleconnections.