Presentation 2003/7/22
Analysis of ensemble learning using simple perceptrons based on on-line learning theory
Seiji MIYOSHI, Kazuyuki HARA, Masato OKADA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We discuss the ensemble learning using K nonlinear simple perceptrons of which an output function is the sign function based on the on-line learning in the finite K case. First, we derive a macroscopic differential equation describing a dynamics of correlation q between the student weight vectors in a general learning algorithm. Second, we apply the equation to the three well-known rules, that is the Hebb rule, the Perceptron rule and the AdaTron rule, and solve those numerically. Third, we obtain the generalization error of these ensemble machines using a majority vote of students. As result, we show that the correlation between the student weight vectors in the AdaTron rule evolves most slowly, and that the AdaTron rule is the most superior among the three learning rules in the framework of the ensemble learning.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) ensemble learning / on-line learning / nonlinear perceptron / Perceptron rule / Hebb rule / AdaTron rule / generalization error
Paper # NC2003-36
Date of Issue

Conference Information
Committee NC
Conference Date 2003/7/22(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) Analysis of ensemble learning using simple perceptrons based on on-line learning theory
Sub Title (in English)
Keyword(1) ensemble learning
Keyword(2) on-line learning
Keyword(3) nonlinear perceptron
Keyword(4) Perceptron rule
Keyword(5) Hebb rule
Keyword(6) AdaTron rule
Keyword(7) generalization error
1st Author's Name Seiji MIYOSHI
1st Author's Affiliation Kobe City College of Technology()
2nd Author's Name Kazuyuki HARA
2nd Author's Affiliation Tokyo Metropolitan College of Technology
3rd Author's Name Masato OKADA
3rd Author's Affiliation RIKEN Brain Science Institute:JST PRESTO
Date 2003/7/22
Paper # NC2003-36
Volume (vol) vol.103
Number (no) 228
Page pp.pp.-
#Pages 6
Date of Issue