Research and Improvement on Error Back Propagation Neural Network and Learning Algorithm

DOI

10.2991/iccsee.2013.107How to use a DOI?

Keywords

Artificial Neural Network, local minimum, BP algorithm, learning rate

Abstract

As the important subfield and the quintessence of Artificial Neural Network, BP Neural Network accelerated the development in this field. BP algorithm uses the steepest descent algorithm, thus there are two main shortcomings of slow convergence rate and easy to fall into local minimum. According to this, this paper researches on the basis of the standard BP algorithm and presented many improved back propagation algorithms from the factor of the learning rate, error function, activation function, optimization algorithm, the network structure and other aspects.

Copyright

© 2013, 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  - Yudong Huang
AU  - Gaoqiang Yang
AU  - Rui Hao
AU  - Jianhe Guan
PY  - 2013/03
DA  - 2013/03
TI  - Research and Improvement on Error Back Propagation Neural Network and Learning Algorithm
BT  - Proceedings of the 2nd International Conference on Computer Science and Electronics Engineering (ICCSEE 2013)
PB  - Atlantis Press
SP  - 418
EP  - 421
SN  - 1951-6851
UR  - https://doi.org/10.2991/iccsee.2013.107
DO  - 10.2991/iccsee.2013.107
ID  - Huang2013/03
ER  -