An Automatic Adjustment Method of Backpropagation Learning Parameters, Using Fuzzy Inference

Fumio UENO  Takahiro INOUE  Kenichi SUGITANI  Badur-ul-Haque BALOCH  Takayoshi YAMAMOTO  

IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences   Vol.E76-A   No.4   pp.631-636
Publication Date: 1993/04/25
Online ISSN: 
Print ISSN: 0916-8508
Type of Manuscript: PAPER
Category: Neural Networks
neural networks,  backpropagation,  fuzzy theory,  

Full Text: PDF(474.5KB)>>
Buy this Article

In this work, we introduce a fuzzy inference in conventional backpropagation learning algorithm, for networks of neuron like units. This procedure repeatedly adjusts the learning parameters and leads the system to converge at the earliest possible time. This technique is appropriate in a sense that optimum learning parameters are being applied in every learning cycle automatically, whereas the conventional backpropagation doesn't contain any well-defined rule regarding the proper determination of the value of learning parameters.