This talk by Josh Tenenbaum was presented as part of the MIT course, 6.S099: Artificial General Intelligence, taught in January, 2018. This course takes an engineering approach to exploring possible research paths toward building human-level intelligence. Josh Tenenbaum highlights some ways that a deep understanding of how the human mind and brain solve complex tasks of general intelligence can provide valuable insights into the design of artificial systems that are able to build models of the world to support explanation, imagination, planning, thinking, and communicating, as flexibly and deeply as humans. 

Video:

    Building machines that see, learn, and think like people (1:35:08)

Additional Resources:

• Josh Tenenbaum’s website
• Battaglia, P. W., Hamrick, J. B. & Tenenbaum, J. B. (2013) Simulation as an engine of physical scene understanding, Proceedings of the National Academy of Sciences 110(45):18327-18332.
• Lake, B. M., Salakhutdinov, R. & Tenenbaum, J. B. (2015) Human-level concept learning through probabilistic program induction, Science 350(6266):1332-1338.
• Lake, B. M., Ullman, T. D., Tenenbaum, J. B. & Gershman, S. J. (2017) Building machines that learn and think like people, Behavioral and Brain Sciences 10:e253.
• Liu, S., Ullman, T. D., Tenenbaum, J. B. & Spelke, E. S. (2017) Ten-month-old infants infer the value of goals from the costs of actions, Science 358:1038-1041.
• Teglas, E., Vul, E., Girotto, V., Gonzalez, M., Tenenbaum, J. B. &  Bonatti, L. L. (2011) Pure reasoning in 12-month-old infants as probabilistic inference, Science 332:1054-1059.