Novel Random k Satisfiability for k ≤ 2 in Hopfield Neural Network

被引：27

作者：

Sathasivam, Saratha ^{[1
]}

Mansor, Mohd Asyraf ^{[2
]}

Ismail, Ahmad Izani Md ^{[1
]}

Jamaludin, Siti Zulaikha Mohd ^{[1
]}

Kasihmuddin, Mohd Shareduwan Mohd ^{[1
]}

Mamat, Mustafa ^{[3
]}

机构：

[1] Univ Sains Malaysia, Sch Math Sci, George Town 11800, Malaysia

[2] Univ Sains Malaysia, Sch Distance Educ, George Town 11800, Malaysia

[3] Univ Sultan Zainal Abidin, Fac Informat & Comp, UniSZA, Kuala Terengganu 21300, Terengganu Daru, Malaysia

来源：

SAINS MALAYSIANA | 2020年 / 49卷 / 11期

关键词：

Artificial neural network; Hopfield neural network; logic programming; random satisfiability; ALGORITHM;

D O I：

10.17576/jsm-2020-4911-23

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

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 (FINN) 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.

引用

页码：2847 / 2857

页数：11

共 50 条

[41] A Novel Multiscroll Memristive Hopfield Neural Network
Li, Ronghao
Dong, Enzeng
Tong, Jigang
Wang, Zenghui
INTERNATIONAL JOURNAL OF BIFURCATION AND CHAOS, 2022, 32 (09):
[42] k-Global stability of Hopfield neural networks
Zhong, Shouming
Yang, Ye
Dianzi Keji Daxue Xuebao/Journal of University of Electronic Science and Technology of China, 1995, 24 (06): : 647 - 651
[43] Optimal Performance Evaluation Metrics For Satisfiability Logic Representation In Discrete Hopfield Neural Network
Mansor, Mohd Asyraf
Sathasivam, Saratha
INTERNATIONAL JOURNAL OF MATHEMATICS AND COMPUTER SCIENCE, 2021, 16 (03): : 963 - 976
[44] k-Global stability of Hopfield neural networks
1600, (24):
[45] Pseudo random number generator based on Hopfield Neural Network
Wang, Yu-Hua
Shen, Zhi-Dong
Zhang, Huan-Guo
PROCEEDINGS OF 2006 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-7, 2006, : 2810 - +
[46] Random Attractors of a Stochastic Hopfield Neural Network Model with Delays
Hu, Wenjie
Zhu, Quanxin
Kloeden, Peter E.
Duan, Yueliang
QUALITATIVE THEORY OF DYNAMICAL SYSTEMS, 2024, 23 (05)
[47] Random sequence generation using clipped hopfield neural network
Chan, Choi-Kuen
Chan, Chi-Kwong
Cheng, L.M.
Advances in Neural Networks and Applications, 2001, : 253 - 255
[48] Satisfiability and Algorithms for Non-uniform Random k-SAT
Omelchenko, Oleksii
Bulatov, Andrei A.
THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 3886 - 3894
[49] Finite-size scaling in random K-satisfiability problems
Lee, Sang Hoon
Ha, Meesoon
Jeon, Chanil
Jeong, Hawoong
PHYSICAL REVIEW E, 2010, 82 (06):
[50] Modified Imperialistic Competitive Algorithm in Hopfield Neural Network for Boolean Three Satisfiability Logic Mining
Zamri, Nur Ezlin
Alway, Alyaa
Mansor, Mohd Asyraf
Kasihmuddin, Mohd Shareduwan Mohd
Sathasivam, Saratha
PERTANIKA JOURNAL OF SCIENCE AND TECHNOLOGY, 2020, 28 (03): : 983 - 1008

← 1 2 3 4 5 →