Synergies in human and machine learning
par
Michael C. Mozer
Department of Computer Science and Institute of Cognitive Science
University of Colorado
Lundi 24 septembre 2018, 10:00-12:00, Salle 3195, Pavillon André-Aisenstadt
Université de Montréal, 2920 Chemin de la Tour
La conférence sera présentée en anglais
Résumé:
My current research focuses on optimizing human learning using machine learning, and also on improving machine learning via insights from human learning. I'll describe a project in which we personalize study schedules for students to promote long-term retention. We incorporate predictive models of human memory into retrieval-practice software to assist students in reviewing previously mastered material. Through a year-long intervention in middle-school foreign language courses, we demonstrate the value of systematic review on long-term educational outcomes, but more specifically, the value of adaptive review that leverages data from a population of learners to personalize recommendations based on an individual's study history and past performance. I will also describe how we are using theories of human learning and memory to inform the design of machine learning algorithms. At a meta level, I am hoping to convince you through this research that cognitive-science theory is valuable in building artificial intelligence.
Bio :
Michael Mozer received a Ph.D. in Cognitive Science from the University of California at San Diego in 1987. Following a postdoctoral fellowship with Geoffrey Hinton at the University of Toronto, he joined the faculty at the University of Colorado at Boulder and is presently an Professor in the Department of Computer Science and the Institute of Cognitive Science. In 2018-19, he is on leave visiting Google Brain. He is secretary of the Neural Information Processing Systems (NIPS) Foundation and has served as program chair and general chair at NIPS and as chair of the Cognitive Science Society. His research interests span human optimization, cognitively-informed machine learning, computational cognitive modeling, and intelligent environments.
