Improvement of GRBM Based on Activation Function

DOI

10.2991/caai-17.2017.104How to use a DOI?

Keywords

component; image recognition; Gaussian Boltzmann machine; ReLu activation function; Softplus activation function; parallel tempering

Abstract

In this paper, inspired by ReLu and Softplus activation function, we propose two improved models of GRBM, called SPC-GRBM and RPC-GRBM, to obtain better recognition results. Different from the traditional activation-function-improved models, SPC-GRBM and RPC-GRBM focus on the visual layer activation function, which is trained by CBCL database and is finally used for image classification with the help of the k-Nearest Neighbor (KNN) method. Experimental results show that the recognition accuracy of SPC-GRBM and RPC-GRBM are both enhanced and SPC-GRBM has achieved the highest recognition rate among the several models particularly, of which the recognition accuracy is 20.10% higher than the original GRBM. In addition, the reconstruction error is apparently reduced and its performance keeps well.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Ting Niu
AU  - Wenjing Huang
AU  - Xiang Gao
PY  - 2017/06
DA  - 2017/06
TI  - Improvement of GRBM Based on Activation Function
BT  - Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)
PB  - Atlantis Press
SP  - 461
EP  - 464
SN  - 1951-6851
UR  - https://doi.org/10.2991/caai-17.2017.104
DO  - 10.2991/caai-17.2017.104
ID  - Niu2017/06
ER  -