IEICE TRANSACTIONS on Fundamentals
Learning of a Multi-Valued Neural Network and Its Application
Summary :
A learning procedure of a three layer neural network with limited structure, called a multi-valued neural network, is proposed. The three layer net has a single linear neuron in its output layer. All input weights of a number of hidden neurons are identical. The network takes k+1 distinct stable values, where k is the number of hidden neurons. The proposed learning procedure consists of two parts, Phase
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.6 pp.873-877
- Publication Date
- 1993/06/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- Special Section PAPER (Special Section on Papers Selected from 1992 Joint Technical Conference on Circuits/Systems,Computers and Communications (JTC-CSCC'92))
- Category
- Nonlinear Circuits and Neural Nets
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Ryuzo TAKIYAMA, Koichiro KUBO, "Learning of a Multi-Valued Neural Network and Its Application" in IEICE TRANSACTIONS on Fundamentals,
vol. E76-A, no. 6, pp. 873-877, June 1993, doi: .
Abstract: A learning procedure of a three layer neural network with limited structure, called a multi-valued neural network, is proposed. The three layer net has a single linear neuron in its output layer. All input weights of a number of hidden neurons are identical. The network takes k+1 distinct stable values, where k is the number of hidden neurons. The proposed learning procedure consists of two parts, Phase
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_6_873/_p
Copy
@ARTICLE{e76-a_6_873,
author={Ryuzo TAKIYAMA, Koichiro KUBO, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Learning of a Multi-Valued Neural Network and Its Application},
year={1993},
volume={E76-A},
number={6},
pages={873-877},
abstract={A learning procedure of a three layer neural network with limited structure, called a multi-valued neural network, is proposed. The three layer net has a single linear neuron in its output layer. All input weights of a number of hidden neurons are identical. The network takes k+1 distinct stable values, where k is the number of hidden neurons. The proposed learning procedure consists of two parts, Phase
keywords={},
doi={},
ISSN={},
month={June},}
Copy
TY - JOUR
TI - Learning of a Multi-Valued Neural Network and Its Application
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 873
EP - 877
AU - Ryuzo TAKIYAMA
AU - Koichiro KUBO
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 6
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - June 1993
AB - A learning procedure of a three layer neural network with limited structure, called a multi-valued neural network, is proposed. The three layer net has a single linear neuron in its output layer. All input weights of a number of hidden neurons are identical. The network takes k+1 distinct stable values, where k is the number of hidden neurons. The proposed learning procedure consists of two parts, Phase
ER -
English
