Presentation | 1997/2/6 Local Feature Learning Algorithm for Acceleration of Learning Process Yoshihiro Hayakawa, Yasuji Sawada, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Neural network whose connection weights can be varied is often used for learning and adaptation systems. There were proposed variety of leaning algorithms, among which "Back Propagation (BP)" is most well known. It is known,however, that BP is much slower man is expected for the "real time learning algorithm". So it is a most important pmblem to develop a fast algorithm for "Ieal time learning". Here in this paper we present a new general and simple algorithm taking account loca1 feature into the original BP algorithm. We obtaind a surprising acceleration rate by this new algorithm. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Neural Network / Learning / accelemtion / Local Feature / BackPropagation |
Paper # | NLP96-130,NC96-84 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1997/2/6(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) | Local Feature Learning Algorithm for Acceleration of Learning Process |
Sub Title (in English) | |
Keyword(1) | Neural Network |
Keyword(2) | Learning |
Keyword(3) | accelemtion |
Keyword(4) | Local Feature |
Keyword(5) | BackPropagation |
1st Author's Name | Yoshihiro Hayakawa |
1st Author's Affiliation | Research Institute of Electrical Communication, Tohoku Univ.() |
2nd Author's Name | Yasuji Sawada |
2nd Author's Affiliation | Research Institute of Electrical Communication, Tohoku Univ. |
Date | 1997/2/6 |
Paper # | NLP96-130,NC96-84 |
Volume (vol) | vol.96 |
Number (no) | 511 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |