Subspace Restricted Boltzmann Machine
Machine Learning
2014-07-17 v1
Abstract
The subspace Restricted Boltzmann Machine (subspaceRBM) is a third-order Boltzmann machine where multiplicative interactions are between one visible and two hidden units. There are two kinds of hidden units, namely, gate units and subspace units. The subspace units reflect variations of a pattern in data and the gate unit is responsible for activating the subspace units. Additionally, the gate unit can be seen as a pooling feature. We evaluate the behavior of subspaceRBM through experiments with MNIST digit recognition task, measuring reconstruction error and classification error.
Cite
@article{arxiv.1407.4422,
title = {Subspace Restricted Boltzmann Machine},
author = {Jakub M. Tomczak and Adam Gonczarek},
journal= {arXiv preprint arXiv:1407.4422},
year = {2014}
}
Comments
7 pages