Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions

スポンサーリンク

概要

• 論文の詳細を見る

• The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.

• 一般社団法人電子情報通信学会の論文
• 1993-04-25

著者

• Takiyama R

  The Department Of Visual Communication Design Kyushu Institute Of Design

• Takiyama Ryuzo

  The Department Of Visual Communication Design Kyushu University Of Design Science

• Fukudome Kimitoshi

  The Department Of Acoustic Design Kyushu Institute Of Design

関連論文

• A Differential-Geometrical Theory of Sensory System Relations between the Psychophysical, the DL and the JND Functions (Special Section on Neural Nets, Chaos and Numerics)
• Learning of a Multi-Valued Neural Network and Its Application : Special Section on JTC-CSCC'92
• Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions

スポンサーリンク