This is a past event. Its details are archived for historical purposes.
The contact information may no longer be valid.
Please visit our current events listings to look for similar events by title, location, or venue.
Friday, February 15, 2019 at 12:20pm to 1:45pm
Goldwin Smith Hall, G76, Lewis Auditorium
Josh Tenenbaum, PhD
Computational Cognitive Science Group
Department of Brain & Cognitive Sciences
Massachusetts Institute of Technology
Engineering & Reverse-Engineering the Core
of Human Common Sense
Despite dramatic advances in artificial intelligence (AI) technologies, we are still far from having any real artificial intelligence. We have machines that do things we used to think only humans could do, but we don’t have machines with anything like the flexible, general-purpose commonsense grasp of the world that we can see in even a one-and-a-half-year-old. Our work focuses on this gap: how can we capture in computational terms the most basic learning and thinking abilities humans possess from early childhood, and how can we use these insights to build more human-like forms of machine intelligence?
While today’s AI technologies are largely driven by pattern recognition, human intelligence goes far beyond that. At the heart of common sense is the ability to model the world, especially the immediate physical and social environment around us: to explain and understand what we see; to imagine things we could see but haven’t yet; to solve problems and plan actions to make these things real; and to build new models as we learn more about the world. I will describe recent work on reverse-engineering these capacities using methods from probabilistic programming, program induction, and program synthesis, which together with deep learning methods and video game simulation engines, provide a toolkit for the joint enterprise of modeling human intelligence and making AI systems smarter in more human-like ways.