A Learning Method of Neural Network with Lattice Architecture

ICHIMURA Takumi, OEDA Shinichi, YAMASHITA Toshiyuki, TAZAKI Eiichiro

doi:10.3156/jfuzzy.14.1_28

Bibliographic Information

Other Title

格子構造ニューラルネットワークによる学習法の提案(<特集>SOMとその応用)
格子構造ニューラルネットワークによる学習法の提案
コウシコウゾウニューラルネットワークニヨルガクシュウホウノテイアン

Search this article

Description

Bp learning has been used very often as methods for neural network's learning. If the network has enough neurons to classify the training data, BP learning is well known to perform good classification. However, the network is so called "Black Box", because it is difficult to give clear explanation on the relation between inputs and outputs. Recently, some methods for extracting some rules from the regularity, which appears on hidden neurons, have been proposed. These methods cannot make clear the relation of extracted rules. In this paper, we propose a learning method of neural network with lattice architecture. This network structure is consisted of hidden neurons in the lattice. To obtain the optimal network structure, we apply a neuron generation/annihilation algorithm without a dependency on an initial network structure. To verify the validity and effectiveness of proposed method, we have experimented to the function identification and classification of any points in a cube to compare with BP learning and RBF network.

Journal

Journal of Japan Society for Fuzzy Theory and Systems

Journal of Japan Society for Fuzzy Theory and Systems 14 (1), 28-42, 2002

Japan Society for Fuzzy Theory and Intelligent Informatics

Keywords

Details 詳細情報について

Export

Report a problem