Back to Search Start Over

Averaged learning equations of error-function-based multilayer perceptrons

Authors :
Junsheng Zhao
Weili Guo
Haikun Wei
Kanjian Zhang
Source :
Neural Computing and Applications. 25:825-832
Publication Year :
2014
Publisher :
Springer Science and Business Media LLC, 2014.

Abstract

The multilayer perceptrons (MLPs) have strange behaviors in the learning process caused by the existing singularities in the parameter space. A detailed theoretical or numerical analysis of the MLPs is difficult due to the non-integrability of the traditional log-sigmoid activation function which leads to difficulties in obtaining the averaged learning equations (ALEs). In this paper, the error function is suggested as the activation function of the MLPs. By solving the explicit expressions of two important expectations, we obtain the averaged learning equations which make it possible for further analysis of the learning dynamics in MLPs. The simulation results also indicate that the ALEs play a significant role in investigating the singular behaviors of MLPs.

Details

ISSN :
14333058 and 09410643
Volume :
25
Database :
OpenAIRE
Journal :
Neural Computing and Applications
Accession number :
edsair.doi...........1e47b903dc892cea00a0559998f1dde8
Full Text :
https://doi.org/10.1007/s00521-014-1557-5