Improvement of GRBM Based on Activation Function
Ting Niu, Wenjing Huang, Xiang Gao
Available Online June 2017.
- https://doi.org/10.2991/caai-17.2017.104How to use a DOI?
- component; image recognition; Gaussian Boltzmann machine; ReLu activation function; Softplus activation function; parallel tempering
- 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.
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 -