Unsupervised learning of latent physical properties using perception-prediction networks
We propose a framework for the completely unsupervised learning of latent object properties from their interactions: the perception-prediction network (PPN). Consisting of a perception module that extracts representations of latent object properties and a prediction module that uses those extracted...
Main Authors: | Zheng, David Y. (Author), Wu, Jiajun (Author), Tenenbaum, Joshua B (Author) |
---|---|
Other Authors: | Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor), Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences (Contributor) |
Format: | Article |
Language: | English |
Published: |
Association For Uncertainty in Artificial Intelligence (AUAI),
2020-08-17T14:22:24Z.
|
Subjects: | |
Online Access: | Get fulltext |
Similar Items
-
Unsupervised learning of latent physical properties using perception-prediction networks
by: Zheng, David Y., M. Eng. Massachusetts Institute of Technology
Published: (2018) -
Unsupervised learning by program synthesis
by: Ellis, Kevin M., et al.
Published: (2018) -
Exploring Latent Information for Unsupervised Person Re-Identification by Discriminative Learning Networks
by: Hongwei Ge, et al.
Published: (2020-01-01) -
Unsupervised learning predicts human perception and misperception of gloss
by: Anderson, B.L, et al.
Published: (2021) -
Unsupervised discovery of parts, structure, and dynamics
by: Xu, Zhenjia, et al.
Published: (2020)