Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability
One of the influential models in the artificial neural network (ANN) research field for addressing the issue of knowledge in the non-systematic logical rule is Random <i>k</i> Satisfiability. In this context, knowledge structure representation is also the potential application of Random...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-07-01
|
Series: | Processes |
Subjects: | |
Online Access: | https://www.mdpi.com/2227-9717/9/8/1292 |
id |
doaj-783e9c3bc04d46e98bfc176af0be3722 |
---|---|
record_format |
Article |
spelling |
doaj-783e9c3bc04d46e98bfc176af0be37222021-08-26T14:15:56ZengMDPI AGProcesses2227-97172021-07-0191292129210.3390/pr9081292Novel Hopfield Neural Network Model with Election Algorithm for Random 3 SatisfiabilityMuna Mohammed Bazuhair0Siti Zulaikha Mohd Jamaludin1Nur Ezlin Zamri2Mohd Shareduwan Mohd Kasihmuddin3Mohd. Asyraf Mansor4Alyaa Alway5Syed Anayet Karim6School of Mathematical Sciences, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Mathematical Sciences, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Distance Education, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Mathematical Sciences, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Distance Education, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Distance Education, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaSchool of Mathematical Sciences, Universiti Sains Malaysia, Gelugor 11800, Penang, MalaysiaOne of the influential models in the artificial neural network (ANN) research field for addressing the issue of knowledge in the non-systematic logical rule is Random <i>k</i> Satisfiability. In this context, knowledge structure representation is also the potential application of Random <i>k</i> Satisfiability. Despite many attempts to represent logical rules in a non-systematic structure, previous studies have failed to consider higher-order logical rules. As the amount of information in the logical rule increases, the proposed network is unable to proceed to the retrieval phase, where the behavior of the Random Satisfiability can be observed. This study approaches these issues by proposing higher-order Random <i>k</i> Satisfiability for <i>k</i> ≤ 3 in the Hopfield Neural Network (HNN). In this regard, introducing the 3 Satisfiability logical rule to the existing network increases the synaptic weight dimensions in Lyapunov’s energy function and local field. In this study, we proposed an Election Algorithm (EA) to optimize the learning phase of HNN to compensate for the high computational complexity during the learning phase. This research extensively evaluates the proposed model using various performance metrics. The main findings of this research indicated the compatibility and performance of Random 3 Satisfiability logical representation during the learning and retrieval phase via EA with HNN in terms of error evaluations, energy analysis, similarity indices, and variability measures. The results also emphasized that the proposed Random 3 Satisfiability representation incorporates with EA in HNN is capable to optimize the learning and retrieval phase as compared to the conventional model, which deployed Exhaustive Search (ES).https://www.mdpi.com/2227-9717/9/8/1292Hopfield Neural Networkrandom 3 satisfiabilityelection algorithmpotential supervised learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Muna Mohammed Bazuhair Siti Zulaikha Mohd Jamaludin Nur Ezlin Zamri Mohd Shareduwan Mohd Kasihmuddin Mohd. Asyraf Mansor Alyaa Alway Syed Anayet Karim |
spellingShingle |
Muna Mohammed Bazuhair Siti Zulaikha Mohd Jamaludin Nur Ezlin Zamri Mohd Shareduwan Mohd Kasihmuddin Mohd. Asyraf Mansor Alyaa Alway Syed Anayet Karim Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability Processes Hopfield Neural Network random 3 satisfiability election algorithm potential supervised learning |
author_facet |
Muna Mohammed Bazuhair Siti Zulaikha Mohd Jamaludin Nur Ezlin Zamri Mohd Shareduwan Mohd Kasihmuddin Mohd. Asyraf Mansor Alyaa Alway Syed Anayet Karim |
author_sort |
Muna Mohammed Bazuhair |
title |
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability |
title_short |
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability |
title_full |
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability |
title_fullStr |
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability |
title_full_unstemmed |
Novel Hopfield Neural Network Model with Election Algorithm for Random 3 Satisfiability |
title_sort |
novel hopfield neural network model with election algorithm for random 3 satisfiability |
publisher |
MDPI AG |
series |
Processes |
issn |
2227-9717 |
publishDate |
2021-07-01 |
description |
One of the influential models in the artificial neural network (ANN) research field for addressing the issue of knowledge in the non-systematic logical rule is Random <i>k</i> Satisfiability. In this context, knowledge structure representation is also the potential application of Random <i>k</i> Satisfiability. Despite many attempts to represent logical rules in a non-systematic structure, previous studies have failed to consider higher-order logical rules. As the amount of information in the logical rule increases, the proposed network is unable to proceed to the retrieval phase, where the behavior of the Random Satisfiability can be observed. This study approaches these issues by proposing higher-order Random <i>k</i> Satisfiability for <i>k</i> ≤ 3 in the Hopfield Neural Network (HNN). In this regard, introducing the 3 Satisfiability logical rule to the existing network increases the synaptic weight dimensions in Lyapunov’s energy function and local field. In this study, we proposed an Election Algorithm (EA) to optimize the learning phase of HNN to compensate for the high computational complexity during the learning phase. This research extensively evaluates the proposed model using various performance metrics. The main findings of this research indicated the compatibility and performance of Random 3 Satisfiability logical representation during the learning and retrieval phase via EA with HNN in terms of error evaluations, energy analysis, similarity indices, and variability measures. The results also emphasized that the proposed Random 3 Satisfiability representation incorporates with EA in HNN is capable to optimize the learning and retrieval phase as compared to the conventional model, which deployed Exhaustive Search (ES). |
topic |
Hopfield Neural Network random 3 satisfiability election algorithm potential supervised learning |
url |
https://www.mdpi.com/2227-9717/9/8/1292 |
work_keys_str_mv |
AT munamohammedbazuhair novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT sitizulaikhamohdjamaludin novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT nurezlinzamri novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT mohdshareduwanmohdkasihmuddin novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT mohdasyrafmansor novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT alyaaalway novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability AT syedanayetkarim novelhopfieldneuralnetworkmodelwithelectionalgorithmforrandom3satisfiability |
_version_ |
1721190392113659904 |