{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T07:41:41Z","timestamp":1772782901835,"version":"3.50.1"},"reference-count":28,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T00:00:00Z","timestamp":1785283200000},"content-version":"am","delay-in-days":240,"URL":"http:\/\/www.elsevier.com\/open-access\/userlicense\/1.0\/"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,1]],"date-time":"2025-12-01T00:00:00Z","timestamp":1764547200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CBET-2143625"],"award-info":[{"award-number":["CBET-2143625"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100023581","name":"National Science Foundation Graduate Research Fellowship Program","doi-asserted-by":"publisher","award":["1745302"],"award-info":[{"award-number":["1745302"]}],"id":[{"id":"10.13039\/100023581","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1016\/j.neunet.2025.107883","type":"journal-article","created":{"date-parts":[[2025,7,19]],"date-time":"2025-07-19T22:23:05Z","timestamp":1752963785000},"page":"107883","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":6,"special_numbering":"C","title":["LeanKAN: a parameter-lean Kolmogorov-Arnold network layer with improved memory efficiency and convergence behavior"],"prefix":"10.1016","volume":"192","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5733-0807","authenticated-orcid":false,"given":"Benjamin C.","family":"Koenig","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7999-1147","authenticated-orcid":false,"given":"Suyong","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3421-7414","authenticated-orcid":false,"given":"Sili","family":"Deng","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.107883_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117699","article-title":"DeepOKAN: Deep operator network based on Kolmogorov Arnold networks for mechanics problems","volume":"436","author":"Abueidda","year":"2025","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"key":"10.1016\/j.neunet.2025.107883_bib0002","unstructured":"Blealtan (2024). Efficient-kan. GitHub repository. Retrieved from https:\/\/github.com\/Blealtan\/efficient-kan."},{"key":"10.1016\/j.neunet.2025.107883_bib0003","unstructured":"Bodner, A. D., Tepsich, A. S., Spolski, J. N., & Pourteau, S., et al. (2024). Convolutional Kolmogorov-Arnold networks. 10.48550\/arXiv.2406.13155."},{"key":"10.1016\/j.neunet.2025.107883_bib0004","unstructured":"Chen, R. T. Q., Rubanova, Y., Bettencourt, J., & Duvenaud, D. (2019). Neural ordinary differential equations. 10.48550\/arXiv.1806.07366."},{"issue":"1","key":"10.1016\/j.neunet.2025.107883_bib0005","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jeconom.2003.10.026","article-title":"On kolmogorov\u2019s representation of functions of several variables by functions of one variable","volume":"123","author":"Coppejans","year":"2004","journal-title":"Journal of Econometrics"},{"key":"10.1016\/j.neunet.2025.107883_bib0006","article-title":"Rodas5 (4)-m\u00e9thodes de rosenbrock d\u2019ordre 5 (4) adapt\u00e9es aux problemes diff\u00e9rentiels-alg\u00e9briques","author":"Di Marzo","year":"1993","journal-title":"MSc Mathematics Thesis, University of Geneva"},{"key":"10.1016\/j.neunet.2025.107883_bib0007","doi-asserted-by":"crossref","unstructured":"Guo, C., Sun, L., Li, S., Yuan, Z., & Wang, C. (2024). Physics-informed Kolmogorov-Arnold network with Chebyshev polynomials for fluid mechanics. 10.48550\/arXiv.2411.04516.","DOI":"10.1063\/5.0284999"},{"issue":"5","key":"10.1016\/j.neunet.2025.107883_bib0008","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107883_bib0009","unstructured":"Howard, A. A., Jacob, B., Murphy, S. H., Heinlein, A., & Stinis, P., et al. (2024). Finite basis Kolmogorov-Arnold networks: Domain decomposition for data-driven and physics-informed problems. 10.48550\/arXiv.2406.19662."},{"issue":"4","key":"10.1016\/j.neunet.2025.107883_bib0010","doi-asserted-by":"crossref","first-page":"725","DOI":"10.1109\/TNN.2003.813830","article-title":"Kolmogorov\u2019s spline network","volume":"14","author":"Igelnik","year":"2003","journal-title":"IEEE Transactions on Neural Networks"},{"key":"10.1016\/j.neunet.2025.107883_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.106333","article-title":"On the Kolmogorov neural networks","volume":"176","author":"Ismayilova","year":"2024","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.107883_bib0012","unstructured":"Kingma, D. P., & Ba, J. (2017). Adam: A Method for Stochastic Optimization. 10.48550\/arXiv.1412.6980."},{"key":"10.1016\/j.neunet.2025.107883_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117397","article-title":"KAN-ODEs: Kolmogorov-Arnold network ordinary differential equations for learning dynamical systems and hidden physics","volume":"432","author":"Koenig","year":"2024","journal-title":"Computer Methods in Applied Mechanics and Engineering"},{"issue":"108(2)","key":"10.1016\/j.neunet.2025.107883_bib0014","article-title":"On the representation of continuous functions of several variables as superpositions of continuous functions of a smaller number of variables","author":"Kolmogorov","year":"1956","journal-title":"Doklady Akademii Nauk"},{"key":"10.1016\/j.neunet.2025.107883_bib0015","unstructured":"Li, Z. (2024). Kolmogorov-Arnold networks are radial basis function networks. 10.48550\/arXiv.2405.06721."},{"key":"10.1016\/j.neunet.2025.107883_bib0016","doi-asserted-by":"crossref","unstructured":"Liu, Z., Ma, P., Wang, Y., Matusik, W., & Tegmark, M., et al. (2024a). KAN 2.0: Kolmogorov-Arnold networks meet science. 10.48550\/arXiv.2408.10205.","DOI":"10.1103\/4t7t-v19l"},{"key":"10.1016\/j.neunet.2025.107883_bib0017","unstructured":"Liu, Z., Wang, Y., Vaidya, S., Ruehle, F., Halverson, J., Solja\u010di\u0107, M., Hou, T. Y., & Tegmark, M. (2024b). KAN: Kolmogorov-Arnold networks. 10.48550\/arXiv.2404.19756."},{"key":"10.1016\/j.neunet.2025.107883_bib0018","unstructured":"Patra, S., Panda, S., Parida, B. K., Arya, M., Jacobs, K., Bondar, D. I., & Abhijit, S., et al. (2024). Physics informed Kolmogorov-Arnold neural networks for dynamical analysis via efficent-KAN and WAV-KAN. 10.48550\/arXiv.2407.18373."},{"key":"10.1016\/j.neunet.2025.107883_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2020.104137","article-title":"A deep machine learning algorithm for construction of the Kolmogorov\u2013Arnold representation","volume":"99","author":"Polar","year":"2021","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.neunet.2025.107883_bib0020","unstructured":"Poluektov, M., & Polar, A. (2021). Probabilistic Kolmogorov-Arnold network. 10.48550\/arXiv.2104.01714."},{"key":"10.1016\/j.neunet.2025.107883_bib0021","unstructured":"Poluektov, M., & Polar, A. (2023). Construction of the Kolmogorov-Arnold representation using the Newton-Kaczmarz method. 10.48550\/arXiv.2305.08194."},{"key":"10.1016\/j.neunet.2025.107883_bib0022","unstructured":"Puri, V. (2024). KolmogorovArnold.jl. GitHub repository. Retrieved from https:\/\/github.com\/vpuri3\/KolmogorovArnold.jl."},{"key":"10.1016\/j.neunet.2025.107883_bib0023","doi-asserted-by":"crossref","unstructured":"Rackauckas, C., Ma, Y., Martensen, J., Warner, C., Zubov, K., Supekar, R., Skinner, D., Ramadhan, A., & Edelman, A. (2021). Universal differential equations for scientific machine learning. 10.48550\/arXiv.2001.04385.","DOI":"10.21203\/rs.3.rs-55125\/v1"},{"issue":"1","key":"10.1016\/j.neunet.2025.107883_bib0024","doi-asserted-by":"crossref","DOI":"10.5334\/jors.151","article-title":"Differentialequations.jl - A performant and feature-rich ecosystem for solving differential equations in Julia","volume":"5","author":"Rackauckas","year":"2017","journal-title":"Journal of Open Research Software"},{"key":"10.1016\/j.neunet.2025.107883_bib0025","unstructured":"Ramachandran, P., Zoph, B., & Le, Q. V. (2017). Searching for activation functions. 10.48550\/arXiv.1710.05941."},{"key":"10.1016\/j.neunet.2025.107883_bib0026","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2021.01.020","article-title":"The Kolmogorov-Arnold representation theorem revisited","volume":"137","author":"Schmidt-Hieber","year":"2021","journal-title":"Neural networks"},{"issue":"2","key":"10.1016\/j.neunet.2025.107883_bib0027","doi-asserted-by":"crossref","first-page":"770","DOI":"10.1016\/j.camwa.2011.06.002","article-title":"Runge-Kutta pairs of order 5(4) satisfying only the first column simplifying assumption","volume":"62","author":"Tsitouras","year":"2011","journal-title":"Computers & Mathematics with Applications"},{"key":"10.1016\/j.neunet.2025.107883_bib0028","doi-asserted-by":"crossref","DOI":"10.1016\/j.cma.2024.117518","article-title":"Kolmogorov Arnold informed neural network: A physics-informed deep learning framework for solving forward and inverse problems based on Kolmogorov Arnold networks","volume":"433","author":"Wang","year":"2025","journal-title":"Computer Methods in Applied Mechanics and Engineering"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025007646?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608025007646?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T06:06:54Z","timestamp":1772777214000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608025007646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":28,"alternative-id":["S0893608025007646"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107883","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"LeanKAN: a parameter-lean Kolmogorov-Arnold network layer with improved memory efficiency and convergence behavior","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.107883","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"107883"}}