Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions
Summary :
The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.
- Publication
- IEICE TRANSACTIONS on Fundamentals Vol.E76-A No.4 pp.637-641
- Publication Date
- 1993/04/25
- Publicized
- Online ISSN
- DOI
- Type of Manuscript
- PAPER
- Category
- Neural Networks
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, Kimitoshi FUKUDOME, "Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions" in IEICE TRANSACTIONS on Fundamentals,
vol. E76-A, no. 4, pp. 637-641, April 1993, doi: .
Abstract: The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.
URL: https://global.ieice.org/en_transactions/fundamentals/10.1587/e76-a_4_637/_p
Copy
@ARTICLE{e76-a_4_637,
author={Ryuzo TAKIYAMA, Kimitoshi FUKUDOME, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions},
year={1993},
volume={E76-A},
number={4},
pages={637-641},
abstract={The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.},
keywords={},
doi={},
ISSN={},
month={April},}
Copy
TY - JOUR
TI - Error-Correction Learning of Three Layer Neural Networks Based on Linear-Homogeneous Expressions
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 637
EP - 641
AU - Ryuzo TAKIYAMA
AU - Kimitoshi FUKUDOME
PY - 1993
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E76-A
IS - 4
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - April 1993
AB - The three layer neural network (TLNN) is treated, where the nonlinearity of a neuron is of signum. First we propose an expression of the discriminant function of the TLNN, which is called a linear-homogeneous expression. This expression allows the differentiation in spite of the signum property of the neuron. Subsequently a learning algorithm is proposed based on the linear-homogeneous form. The algorithm is an error-correction procedure, which gives a mathematical foundation to heuristic error-correction learnings described in various literatures.
ER -
English
