Presentation 2010-10-28
Weight Vector Similarity of Affordable Neural Network by Learning Process
Yoko UWATE, Yoshifumi NISHIO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have recently proposed a novel neural network structure called an "Affordable Neural Network" (AfNN), in which affordable neurons of the hidden layer are considered as cell assembly function observed in human brain function. We have confirmed that the AfNN gains good performance both of the generalization ability and the learning ability. Furthermore, the AfNN has durability, because the AfNN still performs well even if some of neurons in the hidden layer are damaged after learning process. In this study, we study the characteristics of weights of the AfNN during the learning process to make clear the reason of that the AfNNs can perform well for learning and generalization abilities and operate as usually against damaging neurons.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Affordable Neural Network / Vector Similarity / Backpropagation Learning / Pattern Recognition
Paper # NLP2010-90
Date of Issue

Conference Information
Committee NLP
Conference Date 2010/10/21(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) Weight Vector Similarity of Affordable Neural Network by Learning Process
Sub Title (in English)
Keyword(1) Affordable Neural Network
Keyword(2) Vector Similarity
Keyword(3) Backpropagation Learning
Keyword(4) Pattern Recognition
1st Author's Name Yoko UWATE
1st Author's Affiliation Tokushima University()
2nd Author's Name Yoshifumi NISHIO
2nd Author's Affiliation Tokushima University
Date 2010-10-28
Paper # NLP2010-90
Volume (vol) vol.110
Number (no) 255
Page pp.pp.-
#Pages 4
Date of Issue