A Local Search Based Learning Method for Multiple-Valued Logic Networks

Qi-Ping CAO; Zheng TANG; Rong-Long WANG; Xu-Gang WANG

A Local Search Based Learning Method for Multiple-Valued Logic Networks

Qi-Ping CAO, Zheng TANG, Rong-Long WANG , Xu-Gang WANG

Full Text Views

0

Share
Cite this

Summary :

This paper describes a new learning method for Multiple-Value Logic (MVL) networks using the local search method. It is a "non-back-propagation" learning method which constructs a layered MVL network based on canonical realization of MVL functions, defines an error measure between the actual output value and teacher's value and updates a randomly selected parameter of the MVL network if and only if the updating results in a decrease of the error measure. The learning capability of the MVL network is confirmed by simulations on a large number of 2-variable 4-valued problems and 2-variable 16-valued problems. The simulation results show that the method performs satisfactorily and exhibits good properties for those relatively small problems.

Publication: IEICE TRANSACTIONS on Fundamentals Vol.E86-A No.7 pp.1876-1884

Publication Date: 2003/07/01

Publicized

Online ISSN

DOI

Type of Manuscript: PAPER

Category: Neural Networks and Bioengineering

Cite this

Copy

Qi-Ping CAO, Zheng TANG, Rong-Long WANG , Xu-Gang WANG, "A Local Search Based Learning Method for Multiple-Valued Logic Networks" in IEICE TRANSACTIONS on Fundamentals, vol. E86-A, no. 7, pp. 1876-1884, July 2003, doi: .
Abstract: This paper describes a new learning method for Multiple-Value Logic (MVL) networks using the local search method. It is a "non-back-propagation" learning method which constructs a layered MVL network based on canonical realization of MVL functions, defines an error measure between the actual output value and teacher's value and updates a randomly selected parameter of the MVL network if and only if the updating results in a decrease of the error measure. The learning capability of the MVL network is confirmed by simulations on a large number of 2-variable 4-valued problems and 2-variable 16-valued problems. The simulation results show that the method performs satisfactorily and exhibits good properties for those relatively small problems.
URL: https://globals.ieice.org/en_transactions/fundamentals/10.1587/e86-a_7_1876/_p

Copy

@ARTICLE{e86-a_7_1876,
author={Qi-Ping CAO, Zheng TANG, Rong-Long WANG , Xu-Gang WANG, },
journal={IEICE TRANSACTIONS on Fundamentals},
title={A Local Search Based Learning Method for Multiple-Valued Logic Networks},
year={2003},
volume={E86-A},
number={7},
pages={1876-1884},
abstract={This paper describes a new learning method for Multiple-Value Logic (MVL) networks using the local search method. It is a "non-back-propagation" learning method which constructs a layered MVL network based on canonical realization of MVL functions, defines an error measure between the actual output value and teacher's value and updates a randomly selected parameter of the MVL network if and only if the updating results in a decrease of the error measure. The learning capability of the MVL network is confirmed by simulations on a large number of 2-variable 4-valued problems and 2-variable 16-valued problems. The simulation results show that the method performs satisfactorily and exhibits good properties for those relatively small problems.},
keywords={},
doi={},
ISSN={},
month={July},}

Copy

TY - JOUR
TI - A Local Search Based Learning Method for Multiple-Valued Logic Networks
T2 - IEICE TRANSACTIONS on Fundamentals
SP - 1876
EP - 1884
AU - Qi-Ping CAO
AU - Zheng TANG
AU - Rong-Long WANG
AU - Xu-Gang WANG
PY - 2003
DO -
JO - IEICE TRANSACTIONS on Fundamentals
SN -
VL - E86-A
IS - 7
JA - IEICE TRANSACTIONS on Fundamentals
Y1 - July 2003
AB - This paper describes a new learning method for Multiple-Value Logic (MVL) networks using the local search method. It is a "non-back-propagation" learning method which constructs a layered MVL network based on canonical realization of MVL functions, defines an error measure between the actual output value and teacher's value and updates a randomly selected parameter of the MVL network if and only if the updating results in a decrease of the error measure. The learning capability of the MVL network is confirmed by simulations on a large number of 2-variable 4-valued problems and 2-variable 16-valued problems. The simulation results show that the method performs satisfactorily and exhibits good properties for those relatively small problems.
ER -