{"pk":26363,"title":"A Comparative Evaluation of Approximate Probabilistic Simulation and DeepNeural Networks as Accounts of Human Physical Scene Understanding","subtitle":null,"abstract":"Humans demonstrate remarkable abilities to predict physicalevents in complex scenes. Two classes of models for physicalscene understanding have recently been proposed: “IntuitivePhysics Engines”, or IPEs, which posit that people make pre-dictions by running approximate probabilistic simulations incausal mental models similar in nature to video-game physicsengines, and memory-based models, which make judgmentsbased on analogies to stored experiences of previously en-countered scenes and physical outcomes. Versions of the lat-ter have recently been instantiated in convolutional neural net-work (CNN) architectures. Here we report four experimentsthat, to our knowledge, are the first rigorous comparisonsof simulation-based and CNN-based models, where both ap-proaches are concretely instantiated in algorithms that can runon raw image inputs and produce as outputs physical judg-ments such as whether a stack of blocks will fall. Both ap-proaches can achieve super-human accuracy levels and canquantitatively predict human judgments to a similar degree,but only the simulation-based models generalize to novel sit-uations in ways that people do, and are qualitatively consis-tent with systematic perceptual illusions and judgment asym-metries that people show.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"physical scene understanding; neural network;analysis by synthesis; simulation engine; blocks world"}],"section":"Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/4bd5068b","frozenauthors":[{"first_name":"Renqiao","middle_name":"","last_name":"Zhang","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"Jiajun","middle_name":"","last_name":"Wu","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"Chengkai","middle_name":"","last_name":"Zhang","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"William","middle_name":"T.","last_name":"Freeman","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""},{"first_name":"Joshua","middle_name":"B.","last_name":"Tenenbaum","name_suffix":"","institution":"Massachusetts Institute of Technology","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2016-01-01T13:00:00-05:00","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/26363/galley/15999/download/"}]}