Presentation 1998/10/24
The Family of Projection Learnings
Akira HIRABAYASHI, Hidemitsu OGAWA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In feed-forward neural networks, the projection learning(PL), the partial projection learning(PTPL), and the averaged projection learning(APL) are proposed to obtain good generalization ability. The collection of learning methods that involve projections of the original function, including the previous three, are called the family of projection learnings. We propose a new and natural definition of the family of projection learnings, which have concrete and clear physical meanings, unlike previous ones. Based on the new definition, we derive a general form of learning operators. Properties of the family of projection learnings such as noise suppression capability will also be analyzed.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) feedforward neural network / supervised learning / generalization ability / projection learning
Paper # NC98-49
Date of Issue

Conference Information
Committee NC
Conference Date 1998/10/24(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) The Family of Projection Learnings
Sub Title (in English)
Keyword(1) feedforward neural network
Keyword(2) supervised learning
Keyword(3) generalization ability
Keyword(4) projection learning
1st Author's Name Akira HIRABAYASHI
1st Author's Affiliation Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology()
2nd Author's Name Hidemitsu OGAWA
2nd Author's Affiliation Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology
Date 1998/10/24
Paper # NC98-49
Volume (vol) vol.98
Number (no) 365
Page pp.pp.-
#Pages 8
Date of Issue