Global Learning of Neural Networks by Using Hybrid Optimization Algorithm

DOI

10.2991/iske.2007.201How to use a DOI?

Keywords

Neural Networks, Global Learning, Stochastic Approximation, Gradient Descent, Backpropagation Algorithm

Abstract

This paper proposes a global learning of neural networks by hybrid optimization algorithm. The hybrid algorithm combines a stochastic approximation with a gradient descent. The stochastic approximation is first applied for estimating an approximation point inclined toward a global escaping from a local minimum, and then the backpropagation(BP) algorithm is applied for high-speed convergence as gradient descent. The proposed method has been applied to 8-bit parity check and 6-bit symmetry check problems, respectively. The experimental results show that the proposed method has superior convergence performances to the conventional method that is BP algorithm with randomized initial weights setting.

Copyright

© 2007, 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  - Yong-Hyun Cho
AU  - Seong-Jun Hong
PY  - 2007/10
DA  - 2007/10
TI  - Global Learning of Neural Networks by Using Hybrid Optimization Algorithm
BT  - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007)
PB  - Atlantis Press
SP  - 1179
EP  - 1184
SN  - 1951-6851
UR  - https://doi.org/10.2991/iske.2007.201
DO  - 10.2991/iske.2007.201
ID  - Cho2007/10
ER  -