Presentation 1997/5/23
Geometric Learning Algorithm for Elementary Perceptron : Convergence Condition and Noise Performance
Seiji MIYOSHI, Kenji NAKAYAMA, Kazushi IKEDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The geometric learning algorithm (GLA) is proposed for an elementary perceptron. The GLA is a modified version of the affine projection algorithm (APA) for adaptive filters. The convergence conditions of the APA and the GLA are different. The convergence condition of the 1st order GLA for 2 patterns is theoretically derived. The new oncept "the angle of the solution area" is introduced. The computer simulation results support that this new concept is a good estimation of the convergence properties. The noise performance of the 1st order GLA is also analyzed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) perceptron / pattern classification / neural network / geometric learning algorithm / affine projection algorithm
Paper # NC97-5
Date of Issue

Conference Information
Committee NC
Conference Date 1997/5/23(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 Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Geometric Learning Algorithm for Elementary Perceptron : Convergence Condition and Noise Performance
Sub Title (in English)
Keyword(1) perceptron
Keyword(2) pattern classification
Keyword(3) neural network
Keyword(4) geometric learning algorithm
Keyword(5) affine projection algorithm
1st Author's Name Seiji MIYOSHI
1st Author's Affiliation Graduate School of Natural Science and Technology, Kanazawa Univ.:Department of Electronic Eng., Kobe City College of Technology()
2nd Author's Name Kenji NAKAYAMA
2nd Author's Affiliation Department of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ.
3rd Author's Name Kazushi IKEDA
3rd Author's Affiliation Department of Electrical and Computer Eng., Faculty of Eng., Kanazawa Univ.
Date 1997/5/23
Paper # NC97-5
Volume (vol) vol.97
Number (no) 69
Page pp.pp.-
#Pages 8
Date of Issue