Classification using discriminative restricted boltzmann machines (2008)
| Venue: | In ICML ’08: Proceedings of the 25th international conference on Machine learning. ACM |
| Citations: | 27 - 4 self |
BibTeX
@INPROCEEDINGS{Larochelle08classificationusing,
author = {Hugo Larochelle and Yoshua Bengio},
title = {Classification using discriminative restricted boltzmann machines},
booktitle = {In ICML ’08: Proceedings of the 25th international conference on Machine learning. ACM},
year = {2008}
}
Bookmark
 |
 |
 |
 |
 |
 |
OpenURL
Abstract
Recently, many applications for Restricted Boltzmann Machines (RBMs) have been developed for a large variety of learning problems. However, RBMs are usually used as feature extractors for another learning algorithm or to provide a good initialization for deep feed-forward neural network classifiers, and are not considered as a standalone solution to classification problems. In this paper, we argue that RBMs provide a self-contained framework for deriving competitive non-linear classifiers. We present an evaluation of different learning algorithms for RBMs which aim at introducing a discriminative component to RBM training and improve their performance as classifiers. This approach is simple in that RBMs are used directly to build a classifier, rather than as a stepping stone. Finally, we demonstrate how discriminative RBMs can also be successfully employed in a semi-supervised setting.
