DocumentCode
1145664
Title
On the local minima free condition of backpropagation learning
Author
Yu, Xiao-Hu ; Chen, Guo-An
Author_Institution
Dept. of Radio Eng., Southeast Univ., Nanjing, China
Volume
6
Issue
5
fYear
1995
fDate
9/1/1995 12:00:00 AM
Firstpage
1300
Lastpage
1303
Abstract
It is shown that if there are P noncoincident input patterns to learn and a two-layered feedforward neural network having P-1 sigmoidal hidden neuron and one dummy hidden neuron is used for the learning, then any suboptimal equilibrium point of the corresponding error surface is unstable in the sense of Lyapunov. This result leads to a sufficient local minima free condition for the backpropagation learning
Keywords
backpropagation; feedforward neural nets; minimisation; backpropagation learning; dummy hidden neuron; error surface; local minima; local minima free condition; noncoincident input patterns; sigmoidal hidden neuron; suboptimal equilibrium point; two-layered feedforward neural network; Backpropagation algorithms; Binary sequences; Communication channels; Feedforward neural networks; Multi-layer neural network; Neural networks; Neurons; Sufficient conditions; Supervised learning; Training data;
fLanguage
English
Journal_Title
Neural Networks, IEEE Transactions on
Publisher
ieee
ISSN
1045-9227
Type
jour
DOI
10.1109/72.410380
Filename
410380
Link To Document