For Full-Text PDF, please login, if you are a member of IEICE,|
or go to Pay Per View on menu list, if you are a nonmember of IEICE.
A GA-Based Learning Algorithm for Binary Neural Networks
Masanori SHIMADA Toshimichi SAITO
IEICE TRANSACTIONS on Fundamentals of Electronics, Communications and Computer Sciences
Publication Date: 2002/11/01
Print ISSN: 0916-8508
Type of Manuscript: LETTER
Category: Nonlinear Problems
binary neural networks, supervised learning, separating hyperplane, genetic algorithm (GA),
Full Text: PDF>>
This paper presents a flexible learning algorithm for the binary neural network that can realize a desired Boolean function. The algorithm determines hidden layer parameters using a genetic algorithm. It can reduce the number of hidden neurons and can suppress parameters dispersion. These advantages are verified by basic numerical experiments.