Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
Sjoerd van Steenkiste, Michael Chang, Klaus Greff, Jürgen Schmidhuber
Feb 15, 2018 (modified: Feb 16, 2018)ICLR 2018 Conference Blind Submissionreaders: everyoneShow Bibtex
Abstract:Common-sense physical reasoning is an essential ingredient for any intelligent agent operating in the real-world. For example, it can be used to simulate the environment, or to infer the state of parts of the world that are currently unobserved. In order to match real-world conditions this causal knowledge must be learned without access to supervised data. To address this problem we present a novel method that learns to discover objects and model their physical interactions from raw visual images in a purely unsupervised fashion. It incorporates prior knowledge about the compositional nature of human perception to factor interactions between object-pairs and learn efficiently. On videos of bouncing balls we show the superior modelling capabilities of our method compared to other unsupervised neural approaches that do not incorporate such prior knowledge. We demonstrate its ability to handle occlusion and show that it can extrapolate learned knowledge to scenes with different numbers of objects.
TL;DR:We introduce a novel approach to common-sense physical reasoning that learns to discover objects and model their physical interactions from raw visual images in a purely unsupervised fashion
Keywords:Common-sense Physical Reasoning, Intuitive Physics, Representation Learning, Model building
Enter your feedback below and we'll get back to you as soon as possible.