Reverse-engineering core common sense with the tools of probabilistic programs, game-style simulation engines, and inductive program synthesis

Reverse-engineering core common sense with the tools of probabilistic programs, game-style simulation engines, and inductive program synthesis

연구 분야: Analysis

학회: GECCO '21: Proceedings of the Genetic and Evolutionary Computation Conference

None of today's AI systems or approaches comes anywhere close to capturing the common sense of a toddler, or even a 3-month old infant. I will talk about some of the challenges facing conventional machine learning paradigms, such as end-to-end unsupervised learning in deep networks and deep reinforcement learning, and discuss some initial, small steps we have taken with an alternative cognitively-inspired AI approach. This requires us to develop a different engineering toolset, based on probabilistic programs, game-style simulation programs as general-purpose startup software (or "the game engine in the head"), and learning as programming (or "the child as hacker").