LMSS @ Cornell Tech: Alison Gopnik (Berkeley)

Learning Machines Seminar Series What: LMSS: Alison Gopnik (Berkeley) When: Monday, April 20, 10:15 a.m. - 11:15 a.m. Where: Bloomberg 081 The series is organized by Associate Professor Yoav Artzi and sponsored by Bloomberg. Coffee and refreshments will be served at 9:45 a.m. "Empowerment Gain and Causal Model Construction: A Bridge Between Bayesian Hypothesis testing and Reinforcement Learning" Learning about the causal structure of the world is a fundamental problem for human cognition. Causal models and especially causal learning have proved to be difficult for large pretrained models using standard techniques of deep learning. In contrast, cognitive scientists have applied advances in our formal understanding of causation in computer science, particularly within the Causal Bayes Net formalism, to understand human causal learning. In the very different tradition of reinforcement learning, researchers have described an intrinsic reward signal called “empowerment” which maximizes mutual information between actions and their outcomes. “Empowerment” may be an important bridge between classical Bayesian causal learning and reinforcement learning and may help to characterize causal learning in humans and enable it in machines. If an agent learns an accurate causal world model, they will necessarily increase their empowerment, and increasing empowerment will lead to a more accurate causal world model. Empowerment may also explain distinctive features of children’s causal learning, as well as providing a more tractable computational account of how that learning is possible. In empirical studies, we systematically test how children and adults use cues to empowerment to infer causal relations and design effective causal interventions, and compare children and agents in open-ended tasks. BIO Alison Gopnik is professor of psychology and affiliate professor of philosophy at the University of California at Berkeley, and a member of the Berkeley AI Research Group. She received her BA from McGill University and her PhD. from Oxford University. She is a leader in cognitive science, particularly the study of learning and development. She was a founder of the field of “theory of mind”, an originator of the “theory theory” of cognitive development, and the first to apply Bayesian computational models to children’s learning. She has received the APS Lifetime Achievement Cattell and William James Awards, the SRCD Lifetime Achievement Award, the APA Distinguished Scientific Contributions Award, the Bradford Washburn and Carl Sagan Awards for Science Communication, and the Rumelhart Prize for Theoretical Foundations of Cognitive Science. She is a member of the National Academy of Sciences and the American Academy of Arts and Sciences and a Cognitive Science Society, American Association for the Advancement of Science, and Guggenheim Fellow. She was 2022-23 President of the Association for Psychological Science. She has six grandchildren. She is the author of over 160 journal articles and several books including the bestselling and critically acclaimed popular books “The Scientist in the Crib” 1999, “The Philosophical Baby” 2009, and “The Gardener and the Carpenter” 2016. She has written widely about cognitive science and psychology for The Wall Street Journal, The New York Times, The Economist, and The Atlantic, among others. Her TED talk has been viewed more than 5.7 million times. She has frequently appeared on TV, radio and podcasts including “The Colbert Report” and “The Ezra Klein Show”.