17th International Symposium on
Mathematical Theory of Networks and Systems
Kyoto International Conference Hall, Kyoto, Japan, July 24-28, 2006

MTNS 2006 Paper Abstract

Close

Paper TuP01.3

Kondo, Tadashi (The Univ. of Tokushima)

A New Algorithm of Multi-Layered Neural Network Using Heuristic Self-Organization

Scheduled for presentation during the Regular Session "Neural Networks I" (TuP01), Tuesday, July 25, 2006, 16:10−16:35, Room B2

17th International Symposium on Mathematical Theory of Networks and Systems, July 24-28, 2006, Kyoto, Japan

This information is tentative and subject to change. Compiled on April 15, 2024

Keywords Neural networks, Nonlinear system identification

Abstract

In this study, a new algorithm of multi-layered neural network using heuristic self-organization is proposed. We call this algorithm as Group Method of Data Handling(GMDH)-type neural network algorithm self-selecting optimum neural network architecture. The GMDH-type neural network algorithm has an ability of self-selecting optimum neural network architecture from three neural network architectures such as sigmoid function neural network, radial basis function (RBF) neural network and polynomial neural network. The GMDH-type neural network also has abilities of self-selecting the number of layers, the number of neurons in hidden layers and useful input variables.