The Computational Gauntlet of Human-Like Learning

In this talk, I pose a major challenge for AI researchers: to develop systems that learn in a human-like manner. I illustrate this idea with two domains -- mathematics and driving -- where people are effective learners. I review briefly the history of machine learning, noting that early work made close contact with results from cognitive psychology but that this is no longer the case. After this, I identify characteristics of human behavior that can serve as a 'computational gauntlet' and that, if reproduced, will offer better ways to acquire expertise than statistical induction over massive training sets. In addition, I review five AI systems -- some older and others more recent -- that pass most of the gauntlet's obstacles and thus can serve as role models for future work. In closing, I suggest some ways to encourage more research on the important problem of human-like learning.

Speaker: Pat Langley, Center for Design Research

Room 126