A Method of Learning for Multi-Layer Networks

Zheng TANG  Xu Gang WANG  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E85-A   No.2   pp.522-525
Publication Date: 2002/02/01
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Neural Networks and Bioengineering
backpropagation,  local minima,  multi-layer artificial neural networks,  temperature parameter,  gradient ascent,  

Full Text: PDF>>
Buy this Article

A method of learning for multi-layer artificial neural networks is proposed. The learning model is designed to provide an effective means of escape from the Backpropagation local minima. The system is shown to escape from the Backpropagation local minima and be of much faster convergence than simulated annealing techniques by simulations on the exclusive-or problem and the Arabic numerals recognition problem.