{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T06:11:07Z","timestamp":1765260667243,"version":"3.46.0"},"reference-count":34,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T00:00:00Z","timestamp":1764288000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"NIH","award":["2R15EB024283-03"],"award-info":[{"award-number":["2R15EB024283-03"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Axioms"],"abstract":"<jats:p>The Ising model is able to memorize some patterns or solutions as stable states. An Ising network may automatically converge to a pre-stored solution for a random input. However, in many cases, the Ising model cannot perform this task. The gap is that for a set of desired patterns, one may not be able to construct an Ising model such that the desired patterns are the stable solutions of the Ising model. The Ising model has limited power, because its energy function is limited to a second-order polynomial. Our research outline is as follows. This paper extends the conventional Ising model so that it has wider applications, where the Hebbian rule no longer works. The extended model does not have a limit on the order of the energy function. The extended Ising is defined by combining all desired patterns in a product. Our findings are that the extended Ising model has explicit closed-from update formulas, which do not require the evaluation of gradients. Thus, no network training is necessary. The update algorithm takes finite steps to reach a local minimum.<\/jats:p>","DOI":"10.3390\/axioms14120879","type":"journal-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T16:41:41Z","timestamp":1765212101000},"page":"879","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Higher-Order Ising Model with Gradient-Free Update"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-6043","authenticated-orcid":false,"given":"Gengsheng L.","family":"Zeng","sequence":"first","affiliation":[{"name":"Department of Computer Science, Utah Valley University, Orem, UT 84058, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,28]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Lipowski, A. (2022). Ising model: Recent developments and exotic application. Entropy, 24.","DOI":"10.3390\/e24121834"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1038\/s44260-024-00012-0","article-title":"The Ising model celebrates a century of interdisciplinary contributions","volume":"1","author":"Macy","year":"2024","journal-title":"npj Complex"},{"key":"ref_3","unstructured":"K\u00fclske, C. (2025, January 09). The Ising Model: Highlights and Perspectives. Available online: https:\/\/arxiv.org\/html\/2501.05394v1."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Masuda, N., Islam, S., Thu Aung, S., and Watanabe, T. (2025). Energy landscape analysis based on the Ising model: Tutorial review. PLOS Complex Syst., 2.","DOI":"10.1371\/journal.pcsy.0000039"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"052331","DOI":"10.1103\/PhysRevA.77.052331","article-title":"Nonperturbative k-body to two-body commuting conversion Hamiltonians and embedding problem instances into Ising spins","volume":"77","author":"Biamonte","year":"2008","journal-title":"Phys. Rev. A"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Patel, S., Chen, L., Canoza, P., and Salahuddin, S. (2020). Ising model optimization problems on a FPGA accelerated restricted Boltzman machine. arXiv.","DOI":"10.21203\/rs.3.rs-122016\/v1"},{"key":"ref_7","unstructured":"Patel, S., Canoza, P., and Salahuddin, S. (2020). Logically synthesized, hardware-accelerated, restricted Boltzman machines for combinatorial optimization and integer factorization. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Chen, Y., and Zhong, W. (2024). Crossover from anomalous to normal diffusion: Ising model with stochastic resetting. arXiv.","DOI":"10.1103\/PhysRevResearch.6.033189"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Valle, M.A. (2023). The capabilities of Boltzmann machines to detect and reconstruct Ising system\u2019s configurations from a given temperature. Entropy, 25.","DOI":"10.3390\/e25121649"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Gu, J., and Zhang, K. (2022). Thermodynamics of the Ising model encoded in restricted Boltzmann machines. Entropy, 24.","DOI":"10.3390\/e24121701"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1038\/s44335-024-00005-1","article-title":"Solving Boltzmann optimization problems with deep learning","volume":"1","author":"Knoll","year":"2024","journal-title":"npj Unconv. Comput."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Noguer i Alonso, M., and You, C. (2025). The Mathematics of the Ising model and neural networks. SSRN.","DOI":"10.2139\/ssrn.5078967"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1016\/j.cobeha.2021.02.006","article-title":"Hebbian learning revisited and its inference underlying cognitive function","volume":"38","year":"2021","journal-title":"Curr. Opin. Behav. Sci."},{"key":"ref_14","unstructured":"Hebb, D.O. (1949). The Organization of Behavior: A Neuropsychological Theory, John Wiley and Sons, Inc."},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Kisby, C., Blanco, S., and Moss, L. (2022, January 15\u201318). The logic of Hebbian learning. Proceedings of the 35th International Florida Artificial Intelligence Research Society Conference (FLAIRS-35), Jensen Beach, FL, USA.","DOI":"10.32473\/flairs.v35i.130735"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1037\/h0085817","article-title":"A brief history of the Hebbian learning rule","volume":"44","author":"Milner","year":"2003","journal-title":"Can. Psychol. Psychol. Can."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Rojas, R. (1996). The Hopfield model. Neural Networks, Springer.","DOI":"10.1007\/978-3-642-61068-4"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"3999","DOI":"10.1109\/TCSI.2024.3411407","article-title":"Hopfield vs Ising: A comparison on the SoC FPAA","volume":"71","author":"Mathews","year":"2024","journal-title":"IEEE Trans. Circuits Syst. I Regul. Pap."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2554","DOI":"10.1073\/pnas.79.8.2554","article-title":"Neural networks and physical systems with emergent collective computational abilities","volume":"79","author":"Hopfield","year":"1986","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_20","unstructured":"Alonso, N.I. (2024). John Hopfield\u2019s contributions to neural networks: A detailed mathematical exploration. SSRN."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"McAlister, H., Robins, A., and Szymanski, L. (2024). Prototype analysis in Hopfield networks with Hebbian learning. arXiv.","DOI":"10.1162\/neco_a_01704"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Folli, V., Leonetti, M., and Ruocco, G. (2017). On the maximum storage capacity of the Hopfield model. Front. Comput. Neurosci., 10.","DOI":"10.3389\/fncom.2016.00144"},{"key":"ref_23","first-page":"031014","article-title":"Stochastic p-bits for invertible logic","volume":"7","author":"Camsari","year":"2017","journal-title":"Phys. Rev. X"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"613","DOI":"10.1016\/j.shpsc.2004.09.003","article-title":"The early origins of the logit model","volume":"35","author":"Cramer","year":"2004","journal-title":"Stud. Hist. Philos. Sci. Part C Stud. Hist. Philos. Biol. Biomed. Sci."},{"key":"ref_25","first-page":"1","article-title":"Asynchronous iterations in optimization: New sequence results and sharper algorithmic guarantees","volume":"24","author":"Feyzmahdavian","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"6033","DOI":"10.1038\/s41467-023-41214-9","article-title":"Efficient optimization with higher-order Ising machines","volume":"14","author":"Bybee","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"L022301","DOI":"10.1103\/hbh5-3nty","article-title":"Higher-order Ising model on hypergraphs","volume":"112","author":"Robiglio","year":"2025","journal-title":"Phys. Rev. E"},{"key":"ref_28","unstructured":"Cen, Y., Zhang, Z., Wang, Z., Wang, Y., and Fong, X. (2024). Analysis of higher-order Ising Hamiltonians. arXiv."},{"key":"ref_29","unstructured":"Ide, N., Asayama, T., Ueno, H., and Ohzeki, M. (2020, January 24\u201327). Maximum-likelihood channel decoding with quantum annealing machine. Proceedings of the 2020 International Symposium on Information Theory and Its Applications (ISITA), Kapolei, HI, USA."},{"key":"ref_30","unstructured":"Huffman, W.C., and Pless, V. (2010). Fundamentals of Error-Correcting Codes, Cambridge University Press."},{"key":"ref_31","unstructured":"Vanstone, S.A., and Van Oorschot, P.C. (2013). An introduction to Error Correcting Codes with Applications, Springer Science & Business Media."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Punnen, A.P. (2022). The Quadratic Unconstrained Binary Optimization Problem, Springer International Publishing.","DOI":"10.1007\/978-3-031-04520-2"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1002\/net.21751","article-title":"Quadratic unconstrained binary optimization problem preprocessing: Theory and empirical analysis","volume":"70","author":"Lewis","year":"2017","journal-title":"Networks"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"3746","DOI":"10.1016\/j.dam.2009.07.009","article-title":"Analyzing quadratic unconstrained binary optimization problems via multicommodity flows","volume":"157","author":"Wang","year":"2009","journal-title":"Discret. Appl. Math."}],"container-title":["Axioms"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-1680\/14\/12\/879\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T05:11:14Z","timestamp":1765257074000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-1680\/14\/12\/879"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,28]]},"references-count":34,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["axioms14120879"],"URL":"https:\/\/doi.org\/10.3390\/axioms14120879","relation":{},"ISSN":["2075-1680"],"issn-type":[{"type":"electronic","value":"2075-1680"}],"subject":[],"published":{"date-parts":[[2025,11,28]]}}}