Recent Changes - Search:


University of Massachusetts


Learning Causal Models Of Relational Domains

Methods for discovering causal knowledge from observational data have been a persistent topic of AI research for several decades. Essentially all of this work focuses on knowledge representations for propositional domains. In this talk, I give a brief overview of causality. I describe the traditional approach to discovering causal knowledge from data. And from there, I explain why those approaches aren't sufficient and describe recent research efforts that extend causal discovery to relational domains.

Edit - History - Print - Recent Changes - Search
Page last modified on September 17, 2010, at 12:47 AM