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: | , , |
---|---|
Other Authors: | , |
Format: | Article |
Language: | English |
Published: |
Association For Uncertainty in Artificial Intelligence (AUAI),
2020-08-17T14:22:24Z.
|
Subjects: | |
Online Access: | Get fulltext |