Cover Image

Discrete mutation hopfield neural network in propositional satisfiability

The dynamic behaviours of an artificial neural network (ANN) system are strongly dependent on its network structure. Thus, the output of ANNs has long suffered from a lack of interpretability and variation. This has severely limited the practical usability of the logical rule in the ANN. The work pr...

Full description

Saved in:
Bibliographic Details
Main Authors: Mohd. Kasihmuddin, Mohd. Shareduwan, Mansor, Mohd. Asyraf, Md. Basir, Md. Faisal, Sathasivam, Saratha
Format: Article
Language:English
Published: MDPI AG 2019
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/id/eprint/87731/1/MohammadFaisalMohdBasir2019_DiscreteMutationHopfieldNeuralNetwork.pdf
http://eprints.utm.my/id/eprint/87731/
http://dx.doi.org/10.3390/MATH7111133
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.87731
record_format eprints
spelling my.utm.877312020-11-30T13:15:10Z http://eprints.utm.my/id/eprint/87731/ Discrete mutation hopfield neural network in propositional satisfiability Mohd. Kasihmuddin, Mohd. Shareduwan Mansor, Mohd. Asyraf Md. Basir, Md. Faisal Sathasivam, Saratha QA75 Electronic computers. Computer science The dynamic behaviours of an artificial neural network (ANN) system are strongly dependent on its network structure. Thus, the output of ANNs has long suffered from a lack of interpretability and variation. This has severely limited the practical usability of the logical rule in the ANN. The work presents an integrated representation of k-satisfiability (kSAT) in a mutation hopfield neural network (MHNN). Neuron states of the hopfield neural network converge to minimum energy, but the solution produced is confined to the limited number of solution spaces. The MHNN is incorporated with the global search capability of the estimation of distribution algorithms (EDAs), which typically explore various solution spaces. The main purpose is to estimate other possible neuron states that lead to global minimum energy through available output measurements. Furthermore, it is shown that the MHNN can retrieve various neuron states with the lowest minimum energy. Subsequent simulations performed on the MHNN reveal that the approach yields a result that surpasses the conventional hybrid HNN. Furthermore, this study provides a new paradigm in the field of neural networks by overcoming the overfitting issue. MDPI AG 2019-11 Article PeerReviewed application/pdf en http://eprints.utm.my/id/eprint/87731/1/MohammadFaisalMohdBasir2019_DiscreteMutationHopfieldNeuralNetwork.pdf Mohd. Kasihmuddin, Mohd. Shareduwan and Mansor, Mohd. Asyraf and Md. Basir, Md. Faisal and Sathasivam, Saratha (2019) Discrete mutation hopfield neural network in propositional satisfiability. Mathematics, 7 (11). p. 1133. ISSN 2227-7390 http://dx.doi.org/10.3390/MATH7111133
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Mohd. Kasihmuddin, Mohd. Shareduwan
Mansor, Mohd. Asyraf
Md. Basir, Md. Faisal
Sathasivam, Saratha
Discrete mutation hopfield neural network in propositional satisfiability
description The dynamic behaviours of an artificial neural network (ANN) system are strongly dependent on its network structure. Thus, the output of ANNs has long suffered from a lack of interpretability and variation. This has severely limited the practical usability of the logical rule in the ANN. The work presents an integrated representation of k-satisfiability (kSAT) in a mutation hopfield neural network (MHNN). Neuron states of the hopfield neural network converge to minimum energy, but the solution produced is confined to the limited number of solution spaces. The MHNN is incorporated with the global search capability of the estimation of distribution algorithms (EDAs), which typically explore various solution spaces. The main purpose is to estimate other possible neuron states that lead to global minimum energy through available output measurements. Furthermore, it is shown that the MHNN can retrieve various neuron states with the lowest minimum energy. Subsequent simulations performed on the MHNN reveal that the approach yields a result that surpasses the conventional hybrid HNN. Furthermore, this study provides a new paradigm in the field of neural networks by overcoming the overfitting issue.
format Article
author Mohd. Kasihmuddin, Mohd. Shareduwan
Mansor, Mohd. Asyraf
Md. Basir, Md. Faisal
Sathasivam, Saratha
author_facet Mohd. Kasihmuddin, Mohd. Shareduwan
Mansor, Mohd. Asyraf
Md. Basir, Md. Faisal
Sathasivam, Saratha
author_sort Mohd. Kasihmuddin, Mohd. Shareduwan
title Discrete mutation hopfield neural network in propositional satisfiability
title_short Discrete mutation hopfield neural network in propositional satisfiability
title_full Discrete mutation hopfield neural network in propositional satisfiability
title_fullStr Discrete mutation hopfield neural network in propositional satisfiability
title_full_unstemmed Discrete mutation hopfield neural network in propositional satisfiability
title_sort discrete mutation hopfield neural network in propositional satisfiability
publisher MDPI AG
publishDate 2019
url http://eprints.utm.my/id/eprint/87731/1/MohammadFaisalMohdBasir2019_DiscreteMutationHopfieldNeuralNetwork.pdf
http://eprints.utm.my/id/eprint/87731/
http://dx.doi.org/10.3390/MATH7111133
_version_ 1685578980766253056
score 13.211869

Similar Items