Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups

Abstract

The recent successful deep neural networks are largely trained in a supervised manner. It associates complex patterns of input samples with neurons in the last layer, which form representations of concepts. In spite of their successes, the properties of complex patterns associated a learned concept remain elusive. In this work, by analyzing how neurons are… (More)

Topics

2 Figures and Tables

Cite this paper

@article{Li2016AutomaticDO, title={Automatic Discoveries of Physical and Semantic Concepts via Association Priors of Neuron Groups}, author={Shuai Li and Kui Jia and Xiaogang Wang}, journal={CoRR}, year={2016}, volume={abs/1612.09438} }