Presentation 1994/6/17
Perceptron Back Propagation Learning Based on State Optimization
Takeo Ikai, Yasuhiro Yamaguchi, Yoshiaki Kawamura,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a formulation of the back propagation(BP) perceptronlearning by means of Hamiltonian functions.It is proved that the weightobtained by the BP method is the optimal weight minimizing Hamiltonianfunctions and BP learning algorithms are iteration methods to find the optimal weight using the gradient method.Next,the state optimization BP learning is derived which updates weights so as to optimize states(outputs of neurons)in each layer of perceptron.This learning method is perfromedby means of an algorithm for optimizing learning rates.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Perceptron / Back-propagation learning / Hamiltonian functions / Hamiltoian minimization / State optimization / Learning rate optimization
Paper # NLP94-31
Date of Issue

Conference Information
Committee NLP
Conference Date 1994/6/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Nonlinear Problems (NLP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Perceptron Back Propagation Learning Based on State Optimization
Sub Title (in English)
Keyword(1) Perceptron
Keyword(2) Back-propagation learning
Keyword(3) Hamiltonian functions
Keyword(4) Hamiltoian minimization
Keyword(5) State optimization
Keyword(6) Learning rate optimization
1st Author's Name Takeo Ikai
1st Author's Affiliation Faculty of Engineering,University of Osaka Prefecture()
2nd Author's Name Yasuhiro Yamaguchi
2nd Author's Affiliation Faculty of Engineering,University of Osaka Prefecture
3rd Author's Name Yoshiaki Kawamura
3rd Author's Affiliation Faculty of Engineering,University of Osaka Prefecture
Date 1994/6/17
Paper # NLP94-31
Volume (vol) vol.94
Number (no) 98
Page pp.pp.-
#Pages 8
Date of Issue