Proceedings of the 2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)

Improvement of GRBM Based on Activation Function

Authors
Ting Niu, Wenjing Huang, Xiang Gao
Corresponding Author
Ting Niu
Available Online June 2017.
DOI
https://doi.org/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.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
2017 2nd International Conference on Control, Automation and Artificial Intelligence (CAAI 2017)
Part of series
Advances in Intelligent Systems Research
Publication Date
June 2017
ISBN
978-94-6252-360-9
ISSN
1951-6851
DOI
https://doi.org/10.2991/caai-17.2017.104How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

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  - 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  - https://doi.org/10.2991/caai-17.2017.104
ID  - Niu2017/06
ER  -