Emergence of Compositional Representations in Restricted Boltzmann Machines

Abstract

Extracting automatically the complex set of features composing real high-dimensional data is crucial for achieving high performance in machine-learning tasks. Restricted Boltzmann machines (RBM) are empirically known to be efficient for this purpose, and to be able to generate distributed and graded representations of the data. We characterize the… (More)
DOI: 10.1103/PhysRevLett.118.138301

Topics

4 Figures and Tables

Cite this paper

@article{Tubiana2017EmergenceOC, title={Emergence of Compositional Representations in Restricted Boltzmann Machines}, author={J{\'e}r{\^o}me Tubiana and R{\'e}mi Monasson}, journal={Physical review letters}, year={2017}, volume={118 13}, pages={138301} }