By Topic

A systematic synthesis procedure for feedforward neural networks by using the GRBF (generalized radial basis function) network technique

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Miyazaki, A. ; Dept. of Comput. Sci. & Commun. Eng., Kyushu Univ., Fukuoka, Japan ; Yamada, T.

Some of the problems that one should first be able to address when developing a synthesis procedure for feedforward neural nets are considered to be the following: development of a systematic approach to the representation of neural networks, that is, choosing the number of hidden layers and the number of units in each hidden layer required to achieve a given level of performance in a given applications; and development of a systematic procedure for the learning of neural networks, that is, setting the weights of a feedforward neural network by using much of the information contained in a given set of examples of input-output pairs. This paper deals with the two problems above by using the GRBF (generalized radial basis function) network technique closely related to approximation techniques such as generalized splines and regularization theory, and aims to offer a framework within which it is possible to address the problems and provide a systematic synthesis procedure for feedforward neural networks.

Published in:

Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on  (Volume:1 )

Date of Conference:

25-29 Oct. 1993