Novel random k Satisfiability for k ≤ 2 in hopfield neural network
The k Satisfiability logic representation (kSAT) contains valuable information that can be represented in terms of variables. This paper investigates the use of a particular non-systematic logical rule namely Random k Satisfiability (RANkSAT). RANkSAT contains a series of satisfiable clauses but t...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Penerbit Universiti Kebangsaan Malaysia
2020
|
| Online Access: | http://journalarticle.ukm.my/16014/ http://journalarticle.ukm.my/16014/1/23.pdf |
| _version_ | 1848813942919397376 |
|---|---|
| author | Saratha Sathasivam, Mohd. Asyraf Mansor, Ahmad Izani Md Ismail, Siti Zulaikha Mohd Jamaludin, Mohd Shareduwan Mohd Kasihmuddin, Mustafa Mamat, |
| author_facet | Saratha Sathasivam, Mohd. Asyraf Mansor, Ahmad Izani Md Ismail, Siti Zulaikha Mohd Jamaludin, Mohd Shareduwan Mohd Kasihmuddin, Mustafa Mamat, |
| author_sort | Saratha Sathasivam, |
| building | UKM Institutional Repository |
| collection | Online Access |
| description | The k Satisfiability logic representation (kSAT) contains valuable information that can be represented in terms of
variables. This paper investigates the use of a particular non-systematic logical rule namely Random k Satisfiability
(RANkSAT). RANkSAT contains a series of satisfiable clauses but the structure of the formula is determined randomly
by the user. In the present study, RANkSAT representation is successfully implemented in Hopfield Neural Network
(HNN) by obtaining the optimal synaptic weights. We focus on the different regimes for k ≤ 2 by taking advantage of
the non-redundant logical structure, thus obtaining the final neuron state that minimizes the cost function. We also
simulate the performances of RANkSAT logical rule using several performance metrics. The simulated results suggest
that the RANkSAT representation can be embedded optimally in HNN and that the proposed method can retrieve the
optimal final state. |
| first_indexed | 2025-11-15T00:26:13Z |
| format | Article |
| id | oai:generic.eprints.org:16014 |
| institution | Universiti Kebangasaan Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T00:26:13Z |
| publishDate | 2020 |
| publisher | Penerbit Universiti Kebangsaan Malaysia |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | oai:generic.eprints.org:160142020-12-17T05:18:30Z http://journalarticle.ukm.my/16014/ Novel random k Satisfiability for k ≤ 2 in hopfield neural network Saratha Sathasivam, Mohd. Asyraf Mansor, Ahmad Izani Md Ismail, Siti Zulaikha Mohd Jamaludin, Mohd Shareduwan Mohd Kasihmuddin, Mustafa Mamat, The k Satisfiability logic representation (kSAT) contains valuable information that can be represented in terms of variables. This paper investigates the use of a particular non-systematic logical rule namely Random k Satisfiability (RANkSAT). RANkSAT contains a series of satisfiable clauses but the structure of the formula is determined randomly by the user. In the present study, RANkSAT representation is successfully implemented in Hopfield Neural Network (HNN) by obtaining the optimal synaptic weights. We focus on the different regimes for k ≤ 2 by taking advantage of the non-redundant logical structure, thus obtaining the final neuron state that minimizes the cost function. We also simulate the performances of RANkSAT logical rule using several performance metrics. The simulated results suggest that the RANkSAT representation can be embedded optimally in HNN and that the proposed method can retrieve the optimal final state. Penerbit Universiti Kebangsaan Malaysia 2020-11 Article PeerReviewed application/pdf en http://journalarticle.ukm.my/16014/1/23.pdf Saratha Sathasivam, and Mohd. Asyraf Mansor, and Ahmad Izani Md Ismail, and Siti Zulaikha Mohd Jamaludin, and Mohd Shareduwan Mohd Kasihmuddin, and Mustafa Mamat, (2020) Novel random k Satisfiability for k ≤ 2 in hopfield neural network. Sains Malaysiana, 49 (11). pp. 2847-2857. ISSN 0126-6039 https://www.ukm.my/jsm/malay_journals/jilid49bil11_2020/KandunganJilid49Bil11_2020.html |
| spellingShingle | Saratha Sathasivam, Mohd. Asyraf Mansor, Ahmad Izani Md Ismail, Siti Zulaikha Mohd Jamaludin, Mohd Shareduwan Mohd Kasihmuddin, Mustafa Mamat, Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title | Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title_full | Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title_fullStr | Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title_full_unstemmed | Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title_short | Novel random k Satisfiability for k ≤ 2 in hopfield neural network |
| title_sort | novel random k satisfiability for k ≤ 2 in hopfield neural network |
| url | http://journalarticle.ukm.my/16014/ http://journalarticle.ukm.my/16014/ http://journalarticle.ukm.my/16014/1/23.pdf |