Neurocomputational Modeling of Human Physical Scene Understanding
Name
humanphys_ccn.pdf
Description
Accepted version
Size
1.56 MB
Format
Adobe PDF
Checksum (MD5)
32b07f8824a16223b0838563197018ec
Author(s)
Yildirim, Ilker
Smith, Kevin A
Belledonne, Mario E
Wu, Jiajun
Tenenbaum, Joshua B
Date Issued
September 2018
Journal
CCN 2018 Conference on Cognitive Computational Neuroscience
Publisher
Cognitive Computational Neuroscience
Citation
Yildirim, Ilker et al. “Neurocomputational Modeling of Human Physical Scene Understanding.” Paper presented at the CCN 2018 Conference on Cognitive Computational Neuroscience, Philadelphia, Pennsylvania, 5-8 September 2018, Cognitive Computational Neuroscience © 2018 The Author(s)
Version
Author's final manuscript
Abstract
Human scene understanding involves not just localizing objects,but also inferring latent attributes that affect how the scene mightunfold, such as the masses of objects within the scene. Theseattributes can sometimes only be inferred from the dynamicsof a scene, but people can flexibly integrate this information toupdate their inferences. Here we propose a neurally plausibleEfficient Physical Inferencemodel that can generate and updateinferences from videos. This model makes inferences over theinputs to a generative model of physics and graphics, usingan LSTM based recognition network to efficiently approximaterational probabilistic conditioning. We find that this model notonly rapidly and accurately recovers latent object information,but also that its inferences evolve with more information in away similar to human judgments. The model provides a testablehypothesis about the population-level activity in brain regionsunderlying physical reasoning.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
McGovern Institute for Brain Research at MIT
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.32470/CCN.2018.1091-0
