Researchers have explored various non-systematic satisfiability approaches to enhance the interpretability of Discrete Hopfield Neural Networks. A flexible framework for non-systematic satisfiability has been developed to investigate diverse logical structures across dimensions and has improved the lack of neuron variation. However, the logic phase of this approach tends to overlook the distribution and characteristics of literal states, and the ratio of negative literals has not been mentioned with higher-order clauses. In this paper, we propose a new non-systematic logic named Weighted Random $k$ Satisfiability ($k = 1, 3$), which implements the ratio of negative literals in higher-order clauses. The proposed logic, integrated into the Discrete Hopfield Neural Network, established a logical structure by incorporating the ratio of negative literals during the logic phase. This enhancement increased the network's storage capacity, improving its ability to handle complex, high-dimensional problems. The advanced logic was evaluated in the learning phase by various metrics. When the values of the ratio were $r = 0.2$, 0.4, 0.6, and 0.8, the logic demonstrated the potential for better performances and smaller errors. Furthermore, the performance of the proposed logical structure demonstrated a positive impact on the management of synaptic weights. The results indicated that the optimal global minimum solutions are achieved when the ratio of negative literals was set to $r = 0.8$. Compared to the state-of-the-art logical structures, this novel approach has a more significant impact on achieving global minimum solutions, particularly in terms of the ratio of negative literals.
Citation: Xiaoyan Liu, Mohd Shareduwan Mohd Kasihmuddin, Nur Ezlin Zamri, Yunjie Chang, Suad Abdeen, Yuan Gao. Higher order Weighted Random k Satisfiability ($k = 1, 3$) in Discrete Hopfield Neural Network[J]. AIMS Mathematics, 2025, 10(1): 159-194. doi: 10.3934/math.2025009
Researchers have explored various non-systematic satisfiability approaches to enhance the interpretability of Discrete Hopfield Neural Networks. A flexible framework for non-systematic satisfiability has been developed to investigate diverse logical structures across dimensions and has improved the lack of neuron variation. However, the logic phase of this approach tends to overlook the distribution and characteristics of literal states, and the ratio of negative literals has not been mentioned with higher-order clauses. In this paper, we propose a new non-systematic logic named Weighted Random $k$ Satisfiability ($k = 1, 3$), which implements the ratio of negative literals in higher-order clauses. The proposed logic, integrated into the Discrete Hopfield Neural Network, established a logical structure by incorporating the ratio of negative literals during the logic phase. This enhancement increased the network's storage capacity, improving its ability to handle complex, high-dimensional problems. The advanced logic was evaluated in the learning phase by various metrics. When the values of the ratio were $r = 0.2$, 0.4, 0.6, and 0.8, the logic demonstrated the potential for better performances and smaller errors. Furthermore, the performance of the proposed logical structure demonstrated a positive impact on the management of synaptic weights. The results indicated that the optimal global minimum solutions are achieved when the ratio of negative literals was set to $r = 0.8$. Compared to the state-of-the-art logical structures, this novel approach has a more significant impact on achieving global minimum solutions, particularly in terms of the ratio of negative literals.
| [1] |
M. Soori, B. Arezoo, R. Dastres, Artificial intelligence, machine learning and deep learning in advanced robotics, a review, Cogn. Robot., 3 (2023), 54–70. https://doi.org/10.1016/j.cogr.2023.04.001 doi: 10.1016/j.cogr.2023.04.001
|
| [2] |
L. Feng, J. Zhang, Application of artificial neural networks in tendency forecasting of economic growth, Econ. Model., 40 (2014), 76–80. https://doi.org/10.1016/j.econmod.2014.03.024 doi: 10.1016/j.econmod.2014.03.024
|
| [3] |
A. Nikitas, K. Michalakopoulou, E. T. Njoya, D. Karampatzakis, Artificial intelligence, transport and the smart city: definitions and dimensions of a new mobility era, Sustainability, 12 (2020), 2789. https://doi.org/10.3390/su12072789 doi: 10.3390/su12072789
|
| [4] |
M. Özbey, M. Kayri, Investigation of factors affecting transactional distance in E-learning environment with artificial neural networks, Educ. Inf. Technol., 28 (2023), 4399–4427. https://doi.org/10.1007/s10639-022-11346-4 doi: 10.1007/s10639-022-11346-4
|
| [5] |
M. Tkáč, R. Verner, Artificial neural networks in business: two decades of research, Appl. Soft Comput., 38 (2016), 788–804. https://doi.org/10.1016/j.asoc.2015.09.040 doi: 10.1016/j.asoc.2015.09.040
|
| [6] |
H. Chereda, A. Bleckmann, K. Menck, J. Perera-Bel, P. Stegmaier, F. Auer, et al., Explaining decisions of graph convolutional neural networks: patient-specific molecular subnetworks responsible for metastasis prediction in breast cancer, Genome Med., 13 (2021), 1–16. https://doi.org/10.1186/s13073-021-00845-7 doi: 10.1186/s13073-021-00845-7
|
| [7] |
J. J. Hopfield, D. W. Tank, "Neural" computation of decisions in optimization problems, Biol. Cybern., 52 (1985), 141–152. http://doi.org/10.1007/BF00339943 doi: 10.1007/BF00339943
|
| [8] |
K. Pagiamtzis, A. Sheikholeslami, Content-addressable memory (CAM) circuits and architectures: A tutorial and survey, IEEE J. Solid-State Circuits, 41 (2006), 712–727. http://doi.org/10.1109/JSSC.2005.864128 doi: 10.1109/JSSC.2005.864128
|
| [9] |
M. Irfan, A. I. Sanka, Z. Ullah, R. C. Cheung, Reconfigurable content-addressable memory (CAM) on FPGAs: a tutorial and survey, Future Gener. Comput. Syst., 128 (2022), 451–465. https://doi.org/10.1016/j.future.2021.09.037 doi: 10.1016/j.future.2021.09.037
|
| [10] | A. Alway, N. E. Zamri, M. S. Mohd Kasihmuddin, A. Mansor, S. Sathasivam, Palm oil trend analysis via logic mining with Discrete Hopfield Neural Network, Pertanika J. Sci. Technol., 28 (2020), 967–981. |
| [11] |
W. A. T. W. Abdullah, Logic programming on a neural network, Int. J. Intell. Syst., 7 (1992), 513–519. https://doi.org/10.1002/int.4550070604 doi: 10.1002/int.4550070604
|
| [12] |
Y. Xie, A. Srivastava, Anti-SAT: mitigating SAT attack on logic locking, IEEE Trans. Comput.-Aided Design Integr. Circuits Syst., 38 (2018), 199–207. https://doi.org/10.1109/TCAD.2018.2801220 doi: 10.1109/TCAD.2018.2801220
|
| [13] |
F. Ivančić, Z. Yang, M. K. Ganai, A. Gupta, P. Ashar, Efficient SAT-based bounded model checking for software verification, Theor. Comput. Sci., 404 (2008), 256–274. https://doi.org/10.1016/j.tcs.2008.03.013 doi: 10.1016/j.tcs.2008.03.013
|
| [14] |
C. Occhipinti, A. Carnevale, L. Briguglio, A. Iannone, P. Bisconti, SAT: a methodology to assess the social acceptance of innovative AI-based technologies, J. Inf. Commun. Ethics Soc., 21 (2023), 94–111. https://doi.org/10.1108/JICES-09-2021-0095 doi: 10.1108/JICES-09-2021-0095
|
| [15] |
C. Castellini, E. Giunchiglia, A. Tacchella, SAT-based planning in complex domains: concurrency, constraints and nondeterminism, Artif. Intell., 147 (2003), 85–117. https://doi.org/10.1016/S0004-3702(02)00375-2 doi: 10.1016/S0004-3702(02)00375-2
|
| [16] |
H. Youness, M. Osama, A. Hussein, M. Moness, A. M. Hassan, An effective SAT solver utilizing ACO based on heterogeneous systems, IEEE Access, 8 (2020), 102920–102934. https://doi.org/10.1109/ACCESS.2020.2999382 doi: 10.1109/ACCESS.2020.2999382
|
| [17] | S. Sathasivam, Upgrading logic programming in Hopfield network, Sains Malaysiana, 39 (2010), 115–118. |
| [18] |
M. S. Mohd Kasihmuddin, M. A. Mansor, M. F. Md Basir, S. Sathasivam, Discrete mutation Hopfield Neural Network in propositional satisfiability, Mathematics, 7 (2019), 1133. https://doi.org/10.3390/math7111133 doi: 10.3390/math7111133
|
| [19] |
J. Zhu, A. Salhotra, C. R. Meinecke, P. Surendiran, R. Lyttleton, D. Reuter, et al., Solving the 3-satisfiability problem using network‐based biocomputation, Adv. Intell. Syst., 4 (2022), 2200202. https://doi.org/10.1002/aisy.202200202 doi: 10.1002/aisy.202200202
|
| [20] | M. A. Mansor, M. S. M. Kasihmuddin, S. Sathasivam, Artificial immune system paradigm in the Hopfield network for 3-satisfiability problem, Pertanika J. Sci. Technol., 25 (2017), 1173–1188. |
| [21] | M. Mouhoub, Systematic versus non-systematic techniques for solving temporal constraints in a dynamic environment, AI Commun., 17 (2004), 201–211. |
| [22] |
S. Sathasivam, M. A. Mansor, A. I. M. Ismail, S. Z. M. Jamaludin, M. S. M. Kasihmuddin, M. Mamat, Novel random k satisfiability for k≤2 in Hopfield Neural Network, Sains Malays., 49 (2020), 2847–2857. http://doi.org/10.17576/jsm-2020-4911-23 doi: 10.17576/jsm-2020-4911-23
|
| [23] |
S. A. Karim, N. E. Zamri, A. Alway, M. S. M. Kasihmuddin, A. I. M. Ismail, M. A. Mansor, et al., Random satisfiability: a higher-order logical approach in Discrete Hopfield Neural Network, IEEE Access, 9 (2021), 50831–50845. http://doi.org/10.1109/ACCESS.2021.3068998 doi: 10.1109/ACCESS.2021.3068998
|
| [24] |
A. Alway, N. E. Zamri, S. A. Karim, M. A. Mansor, M. S. Mohd Kasihmuddin, M. Mohammed Bazuhair, Major 2 satisfiability logic in Discrete Hopfield Neural Network, Int. J. Comput. Math., 99 (2022), 924–948. http://doi.org/10.1080/00207160.2021.1939870 doi: 10.1080/00207160.2021.1939870
|
| [25] |
Y. Guo, M. S. M. Kasihmuddin, Y. Gao, M. A. Mansor, H. A. Wahab, N. E. Zamri, et al., YRAN2SAT: a novel flexible random satisfiability logical rule in Discrete Hopfield Neural Network, Adv. Eng. Softw., 171 (2022), 103169. https://doi.org/10.1016/j.advengsoft.2022.103169 doi: 10.1016/j.advengsoft.2022.103169
|
| [26] |
Y. Gao, Y. Guo, N. A. Romli, M. S. M. Kasihmuddin, W. Chen, M. A. Mansor, et al., GRAN3SAT: creating flexible higher-order logic satisfiability in the Discrete Hopfield Neural Network, Mathematics, 10 (2022), 1899. https://doi.org/10.3390/math10111899 doi: 10.3390/math10111899
|
| [27] |
A. Darmann, J. Döcker, B. Dorn, The monotone satisfiability problem with bounded variable appearances, Int. J. Found. Comput. Sci., 29 (2018), 979–993. https://doi.org/10.1142/S0129054118500168 doi: 10.1142/S0129054118500168
|
| [28] |
N. E. Zamri, S. A. Azhar, M. A. Mansor, A. Alway, M. S. M. Kasihmuddin, Weighted Random k Satisfiability for k = 1, 2 (r2SAT) in Discrete Hopfield Neural Network, Appl. Soft Comput., 126 (2022), 109312. https://doi.org/10.1016/j.asoc.2022.109312 doi: 10.1016/j.asoc.2022.109312
|
| [29] |
S. Mertens, Exhaustive search for low-autocorrelation binary sequences, J. Phys. A: Math. Gen., 29 (1996), L473. https://doi.org/10.1088/0305-4470/29/18/005 doi: 10.1088/0305-4470/29/18/005
|
| [30] |
C. A. Coello, An updated survey of GA-based multiobjective optimization techniques, ACM Comput. Surv. (CSUR), 32 (2000), 109–143. https://doi.org/10.1145/358923.358929 doi: 10.1145/358923.358929
|
| [31] |
A. H. Hassanat, K. Almohammadi, E. Alkafaween, E. Abunawas, A. Hammouri, V. B. S. Prasath, Choosing mutation and crossover ratios for genetic algorithms—a review with a new dynamic approach, Information, 10 (2019), 390. https://doi.org/10.3390/info10120390 doi: 10.3390/info10120390
|
| [32] |
Z. Wang, Z. Liang, R. Zeng, H. Yuan, R. S. Srinivasan, Identifying the optimal heterogeneous ensemble learning model for building energy prediction using the exhaustive search method, Energy Buildings, 281 (2023), 112763. https://doi.org/10.1016/j.enbuild.2022.112763 doi: 10.1016/j.enbuild.2022.112763
|
| [33] |
X. Wang, X. Zhang, L. Dong, H. Liu, Q. Wu, R. Mohan, Development of methods for beam angle optimization for IMRT using an accelerated exhaustive search strategy, Int. J. Radiat. Oncol. Biol. Phys., 60 (2004), 1325–1337. https://doi.org/10.1016/j.ijrobp.2004.06.007 doi: 10.1016/j.ijrobp.2004.06.007
|
| [34] |
A. Darmann, J. Döcker, On simplified NP-complete variants of Monotone 3-Sat, Discrete Appl. Math., 292 (2021), 45–58. http://doi.org/10.1016/j.dam.2020.12.010 doi: 10.1016/j.dam.2020.12.010
|
| [35] |
M. A. Mansor, S. Sathasivam, Accelerating activation function for 3-satisfiability logic programming, Int. J. Intell. Syst. Appl., 8 (2016), 44–50. http://doi.org/10.5815/ijisa.2016.10.05 doi: 10.5815/ijisa.2016.10.05
|
| [36] |
R. Ma, Y. Xie, S. Zhang, W. Liu, Convergence of discrete delayed Hopfield neural networks, Comput. Math. Appl., 57 (2009), 1869–1876. https://doi.org/10.1016/j.camwa.2008.10.006 doi: 10.1016/j.camwa.2008.10.006
|
| [37] |
O. I. Abiodun, A. Jantan, A. E. Omolara, K. V. Dada, N. A. Mohamed, H. Arshad, State-of-the-art in artificial neural network applications: a survey, Heliyon, 4 (2018), e00938. https://doi.org/10.1016/j.heliyon.2018.e00938 doi: 10.1016/j.heliyon.2018.e00938
|
| [38] |
A. Nabi, J. Moehlis, Single input optimal control for globally coupled neuron networks, J. Neural Eng., 8 (2011), 065008. https://doi.org/10.1088/1741-2560/8/6/065008 doi: 10.1088/1741-2560/8/6/065008
|
| [39] |
S. S. Muhammad Sidik, N. E. Zamri, M. S. Mohd Kasihmuddin, H. A. Wahab, Y. Guo, M. A. Mansor, Non-systematic weighted satisfiability in Discrete Hopfield Neural Network using binary artificial bee colony optimization, Mathematics, 10 (2022), 1129. http://doi.org/10.3390/math10071129 doi: 10.3390/math10071129
|
| [40] |
A. Jierula, S. Wang, T. M. Oh, P. Wang, Study on accuracy metrics for evaluating the predictions of damage locations in deep piles using artificial neural networks with acoustic emission data, Appl. Sci., 11 (2021), 2314. https://doi.org/10.3390/app11052314 doi: 10.3390/app11052314
|
| [41] | C. J. Willmott, K. Matsuura, Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance, Climate Res., 30 (2005), 79–82. |
| [42] |
D. Chicco, M. J. Warrens, G. Jurman, The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation, PeerJ Comput. Sci., 7 (2021), e623. https://doi.org/10.7717/peerj-cs.623 doi: 10.7717/peerj-cs.623
|
| [43] |
S. Fletcher, M. Z. Islam, Comparing sets of patterns with the Jaccard index, Australas. J. Inf. Syst., 22 (2018). https://doi.org/10.3127/ajis.v22i0.1538 doi: 10.3127/ajis.v22i0.1538
|
| [44] |
M. Tantardini, F. Ieva, L. Tajoli, C. Piccardi, Comparing methods for comparing networks, Sci. Rep., 9 (2019), 17557. https://doi.org/10.1038/s41598-019-53708-y doi: 10.1038/s41598-019-53708-y
|
| [45] | A. Strehl, J. Ghosh, R. Mooney, Impact of similarity measures on web-page clustering, AAAI Workshop Papers 2000, 2000, 58–64. |
| [46] |
H. K. Sharma, K. Kumari, S. Kar, A rough set approach for forecasting models, Decis. Making: Appl. Manag. Eng., 3 (2020), 1–21. https://doi.org/10.31181/dmame2003001s doi: 10.31181/dmame2003001s
|
| [47] | S. Sathasivam, M. Mamat, M. S. M. Kasihmuddin, M. A. Mansor, Metaheuristics approach for maximum k satisfiability in restricted neural symbolic integration, Pertanika J. Sci. Technol., 28 (2020), 545–564. |
| [48] |
W. Huang, Y. Li, Y. Huang, Deep hybrid neural network and improved differential neuroevolution for chaotic time series prediction, IEEE Access, 8 (2020), 159552–159565. https://doi.org/10.1109/ACCESS.2020.3020801 doi: 10.1109/ACCESS.2020.3020801
|
| [49] |
S. Bag, S. K. Kumar, M. K. Tiwari, An efficient recommendation generation using relevant Jaccard similarity, Inf. Sci., 483 (2019), 53–64. https://doi.org/10.1016/j.ins.2019.01.023 doi: 10.1016/j.ins.2019.01.023
|
| [50] |
A. A. Jalal, A. A. Jasim, A. A. Mahawish, A web content mining application for detecting relevant pages using Jaccard similarity, Int. J. Electr. Comput. Eng., 12 (2022), 6461. https://doi.org/10.11591/ijece.v12i6.pp6461-6471 doi: 10.11591/ijece.v12i6.pp6461-6471
|
| [51] | T. Ng, A. Lopez-Rodriguez, V. Balntas, K. Mikolajczyk, Reassessing the limitations of CNN methods for camera pose regression, arXiv preprint, 2021. https://doi.org/10.48550/arXiv.2108.07260 |
| [52] |
M. Waqas, U. W. Humphries, A critical review of RNN and LSTM variants in hydrological time series predictions, MethodsX, 13 (2024), 102946. https://doi.org/10.1016/j.mex.2024.102946 doi: 10.1016/j.mex.2024.102946
|
| [53] |
S. Manzhos, Q. G. Chen, W. Y. Lee, Y. Heejoo, M. Ihara, C. C. Chueh, Computational investigation of the potential and limitations of machine learning with neural network circuits based on synaptic transistors, J. Phys. Chem. Lett., 15 (2024), 6974–6985. https://doi.org/10.1021/acs.jpclett.4c01413 doi: 10.1021/acs.jpclett.4c01413
|
| [54] |
N. E. Zamri, M. A. Mansor, M. S. M. Kasihmuddin, S. S. Sidik, A. Alway, N. A. Romli, et al., A modified reverse-based analysis logic mining model with Weighted Random 2 Satisfiability logic in Discrete Hopfield Neural Network and multi-objective training of Modified Niched Genetic Algorithm, Expert Syst. Appl., 240 (2024), 122307. https://doi.org/10.1016/j.eswa.2023.122307 doi: 10.1016/j.eswa.2023.122307
|
| [55] |
S. Z. M. Jamaludin, N. A. Romli, M. S. M. Kasihmuddin, A. Baharum, M. A. Mansor, M. F. Marsani, Novel logic mining incorporating log linear approach, J. King Saud Univ.-Comput. Inf. Sci., 34 (2022), 9011–9027. https://doi.org/10.1016/j.jksuci.2022.08.026 doi: 10.1016/j.jksuci.2022.08.026
|
| [56] |
G. Manoharam, M. S. M. Kasihmuddin, S. N. F. M. A. Antony, N. A. Romli, N. A. Rusdi, S. Abdeen, et al., Log-linear-based logic mining with multi-Discrete Hopfield Neural Network, Mathematics, 11 (2023), 2121. https://doi.org/10.3390/math11092121 doi: 10.3390/math11092121
|
| [57] |
N. A. Rusdi, M. S. M. Kasihmuddin, N. A. Romli, G. Manoharam, M. A. Mansor, Multi-unit Discrete Hopfield Neural Network for higher order supervised learning through logic mining: optimal performance design and attribute selection, J. King Saud Univ.-Comput. Inf. Sci., 35 (2023), 101554. https://doi.org/10.1016/j.jksuci.2023.101554 doi: 10.1016/j.jksuci.2023.101554
|
Figures(11) / Tables(8)
Xiaoyan Liu, Mohd Shareduwan Mohd Kasihmuddin, Nur Ezlin Zamri, Yunjie Chang, Suad Abdeen, Yuan Gao. Higher order Weighted Random k Satisfiability ($k = 1, 3$) in Discrete Hopfield Neural Network[J]. AIMS Mathematics, 2025, 10(1): 159-194. doi: 10.3934/math.2025009
DownLoad: