{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T03:56:24Z","timestamp":1781150184928,"version":"3.54.1"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.neunet.2026.108888","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T18:11:41Z","timestamp":1774462301000},"page":"108888","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":2,"special_numbering":"C","title":["rKAN: Rational Kolmogorov-Arnold networks"],"prefix":"10.1016","volume":"201","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9505-819X","authenticated-orcid":false,"given":"Alireza Afzal","family":"Aghaei","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3040-1801","authenticated-orcid":false,"given":"Mehdi","family":"Hosseinzadeh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5946-0771","authenticated-orcid":false,"given":"Kourosh","family":"Parand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.108888_bib0001","doi-asserted-by":"crossref","DOI":"10.1109\/ACCESS.2024.3462297","article-title":"Ckan: Convolutional kolmogorov\u2013arnold networks model for intrusion detection in iot environment","author":"Abd Elaziz","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.108888_bib0002","article-title":"Fkan: Fractional kolmogorov\u2013arnold networks with trainable jacobi basis functions","volume":"623","author":"Aghaei","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2026.108888_bib0003","unstructured":"Aghaei, A. A., Parand, K., Nikkhah, A., & Jaberi, S. (2023). Solving Falkner-Skan type equations via Legendre and Chebyshev neural blocks. arXiv: 2308.03337."},{"issue":"5","key":"10.1016\/j.neunet.2026.108888_bib0004","doi-asserted-by":"crossref","first-page":"2374","DOI":"10.1109\/TNNLS.2021.3106574","article-title":"Rational continuous neural network identifier for singular perturbed systems with uncertain dynamical models","volume":"34","author":"Andrianova","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.neunet.2026.108888_bib0005","unstructured":"Azam, B., & Akhtar, N. (2024). Suitability of KANs for Computer Vision: A preliminary investigation, arXiv: 2406.09087."},{"key":"10.1016\/j.neunet.2026.108888_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.matcom.2024.06.009","article-title":"Solving a class of thomas\u2013Fermi equations: A new solution concept based on physics-informed machine learning","author":"Babaei","year":"2024","journal-title":"Mathematics and Computers in Simulation"},{"issue":"1","key":"10.1016\/j.neunet.2026.108888_bib0007","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1016\/0022-247X(61)90042-7","article-title":"The pad\u00e9 approximant","volume":"2","author":"Baker Jr","year":"1961","journal-title":"Journal of Mathematical Analysis and Applications"},{"key":"10.1016\/j.neunet.2026.108888_bib0008","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1007\/BF01200370","article-title":"Surface approximation with rational B-splines","volume":"6","author":"Bardis","year":"1990","journal-title":"Engineering with Computers"},{"key":"10.1016\/j.neunet.2026.108888_bib0009","unstructured":"Biswas, K., Banerjee, S., & Pandey, A. K. (2021). Orthogonal-Pad\u00e9 Activation Functions: Trainable Activation functions for smooth and faster convergence in deep networks. arXiv: 2106.09693."},{"key":"10.1016\/j.neunet.2026.108888_bib0010","first-page":"14243","article-title":"Rational neural networks","volume":"33","author":"Boull\u00e9","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"6","key":"10.1016\/j.neunet.2026.108888_bib0011","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/0893-9659(92)90014-Z","article-title":"Defeating the runge phenomenon for equispaced polynomial interpolation via tikhonov regularization","volume":"5","author":"Boyd","year":"1992","journal-title":"Applied Mathematics Letters"},{"key":"10.1016\/j.neunet.2026.108888_bib0012","series-title":"Chebyshev and Fourier spectral methods","author":"Boyd","year":"2001"},{"key":"10.1016\/j.neunet.2026.108888_bib0013","doi-asserted-by":"crossref","unstructured":"Bozorgasl, Z., & Chen, H. (2024). Wav-kan: Wavelet kolmogorov-arnold networks. arXiv: 2405.12832.","DOI":"10.2139\/ssrn.4835325"},{"key":"10.1016\/j.neunet.2026.108888_bib0014","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1007\/s00365-009-9054-2","article-title":"On a constructive proof of kolmogorov\u2019s superposition theorem","volume":"30","author":"Braun","year":"2009","journal-title":"Constructive Approximation"},{"key":"10.1016\/j.neunet.2026.108888_bib0015","unstructured":"Cheon, M. (2024). Kolmogorov-Arnold Network for Satellite Image Classification in Remote Sensing. arXiv: 2406.00600."},{"key":"10.1016\/j.neunet.2026.108888_bib0016","unstructured":"Clevert, D.-A., Unterthiner, T., & Hochreiter, S. (2015). Fast and accurate deep network learning by exponential linear units (elus). arXiv: 1511.07289."},{"key":"10.1016\/j.neunet.2026.108888_bib0017","article-title":"A novel neural network architecture for solving fractional differential equations","author":"Dana Mazraeh","year":"2025","journal-title":"Computational Methods for Differential Equations"},{"key":"10.1016\/j.neunet.2026.108888_bib0018","unstructured":"Dzhenzher, S., & Skopenkov, A. (2021). A structured proof of Kolmogorov\u2019s Superposition Theorem. arXiv: 2105.00408."},{"key":"10.1016\/j.neunet.2026.108888_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.eij.2025.100666","article-title":"TFKAN: Transformer based on kolmogorov\u2013Arnold networks for intrusion detection in IoT environment","volume":"30","author":"Fares","year":"2025","journal-title":"Egyptian Informatics Journal"},{"key":"10.1016\/j.neunet.2026.108888_bib0020","doi-asserted-by":"crossref","DOI":"10.1109\/OJCOMS.2025.3569301","article-title":"Deep transfer learning based on hybrid swin transformers with LSTM for intrusion detection systems in IoT environment","author":"Fares","year":"2025","journal-title":"IEEE Open Journal of the Communications Society"},{"key":"10.1016\/j.neunet.2026.108888_bib0021","doi-asserted-by":"crossref","first-page":"305","DOI":"10.1007\/s00034-017-0554-1","article-title":"Super-gaussian bss using fast-ica with chebyshev\u2013pade approximant","volume":"37","author":"He","year":"2018","journal-title":"Circuits, Systems, and Signal Processing"},{"key":"10.1016\/j.neunet.2026.108888_bib0022","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1007\/BF01212365","article-title":"Neural networks, rational functions, and realization theory","volume":"8","author":"Helmke","year":"1995","journal-title":"Mathematics of Control, Signals and Systems"},{"key":"10.1016\/j.neunet.2026.108888_bib0023","series-title":"Polytropes: applications in astrophysics and related fields","volume":"vol. 306","author":"Horedt","year":"2004"},{"key":"10.1016\/j.neunet.2026.108888_bib0024","unstructured":"Kiamari, M., Kiamari, M., & Krishnamachari, B. (2024). GKAN: Graph Kolmogorov-Arnold Networks. arXiv: 2406.06470."},{"issue":"6","key":"10.1016\/j.neunet.2026.108888_bib0025","doi-asserted-by":"crossref","first-page":"928","DOI":"10.1162\/neco.1993.5.6.928","article-title":"Rational function neural network","volume":"5","author":"Leung","year":"1993","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2026.108888_bib0026","unstructured":"Li, C., Liu, X., Li, W., Wang, C., Liu, H., & Yuan, Y. (2024). U-KAN Makes Strong Backbone for Medical Image Segmentation and Generation, arXiv: 2406.02918."},{"key":"10.1016\/j.neunet.2026.108888_bib0027","unstructured":"Li, Z. (2024). Kolmogorov-Arnold Networks are Radial Basis Function Networks. arXiv: 2405.06721."},{"key":"10.1016\/j.neunet.2026.108888_bib0028","series-title":"The thirteenth international conference on learning representations","article-title":"KAN: Kolmogorov\u2013arnold networks","author":"Liu","year":"2025"},{"key":"10.1016\/j.neunet.2026.108888_bib0029","article-title":"GEPINN: An innovative hybrid method for a symbolic solution to the lane-Emden type equation based on grammatical evolution and physics-informed neural networks","author":"Mazraeh","year":"2024","journal-title":"Astronomy and Computing"},{"key":"10.1016\/j.neunet.2026.108888_bib0030","unstructured":"Molina, A., Schramowski, P., & Kersting, K. (2019). Pad\u00e9 activation units: End-to-end learning of flexible activation functions in deep networks. arXiv: 1907.06732."},{"key":"10.1016\/j.neunet.2026.108888_bib0031","doi-asserted-by":"crossref","unstructured":"Nehma, G., & Tiwari, M. (2024). Leveraging KANs For Enhanced Deep Koopman Operator Discovery. arXiv: 2406.02875.","DOI":"10.2139\/ssrn.4905153"},{"key":"10.1016\/j.neunet.2026.108888_bib0032","series-title":"Learning with fractional orthogonal kernel classifiers in support vector machines: Theory, algorithms and applications","author":"Rad","year":"2023"},{"key":"10.1016\/j.neunet.2026.108888_bib0033","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1016\/j.neunet.2021.01.020","article-title":"The kolmogorov\u2013Arnold representation theorem revisited","volume":"137","author":"Schmidt-Hieber","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.108888_bib0034","unstructured":"Seydi, S. T. (2024). Unveiling the Power of Wavelets: A Wavelet-based Kolmogorov-Arnold Network for Hyperspectral Image Classification. arXiv: 2406.07869."},{"key":"10.1016\/j.neunet.2026.108888_bib0035","series-title":"Spectral methods: algorithms, analysis and applications","volume":"vol. 41","author":"Shen","year":"2011"},{"key":"10.1016\/j.neunet.2026.108888_bib0036","doi-asserted-by":"crossref","unstructured":"Shukla, K., Toscano, J. D., Wang, Z., Zou, Z., & Karniadakis, G. E. (2024). A comprehensive and FAIR comparison between MLP and KAN representations for differential equations and operator networks. arXiv: 2406.02917.","DOI":"10.2139\/ssrn.4858126"},{"key":"10.1016\/j.neunet.2026.108888_bib0037","unstructured":"Somvanshi, S., Javed, S. A., Islam, M. M., Pandit, D., & Das, S. (2024). A Survey on Kolmogorov-Arnold Network. arXiv: 2411.06078."},{"key":"10.1016\/j.neunet.2026.108888_bib0038","unstructured":"SS, S. (2024). Chebyshev Polynomial-Based Kolmogorov-Arnold Networks: An Efficient Architecture for Nonlinear Function Approximation. arXiv: 2405.07200."},{"issue":"6","key":"10.1016\/j.neunet.2026.108888_bib0039","doi-asserted-by":"crossref","first-page":"1206","DOI":"10.1093\/jge\/gxad079","article-title":"Rational function neural networks for learning rock physics models from field data","volume":"20","author":"Sun","year":"2023","journal-title":"Journal of Geophysics and Engineering"},{"key":"10.1016\/j.neunet.2026.108888_bib0040","doi-asserted-by":"crossref","unstructured":"Ta, H.-T. (2024). BSRBF-KAN: A combination of B-splines and Radial Basic Functions in Kolmogorov-Arnold Networks, arXiv: 2406.11173.","DOI":"10.1007\/978-981-96-4288-5_1"},{"key":"10.1016\/j.neunet.2026.108888_bib0041","series-title":"Proceedings of the 34th international conference on machine learning","first-page":"3387","article-title":"Neural networks and rational functions","volume":"vol. 70","author":"Telgarsky","year":"2017"},{"issue":"06","key":"10.1016\/j.neunet.2026.108888_bib0042","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1109\/MCG.1983.263244","article-title":"Rational B-splines for curve and surface representation","volume":"3","author":"Tiller","year":"1983","journal-title":"IEEE Computer Graphics and Applications"},{"key":"10.1016\/j.neunet.2026.108888_bib0043","doi-asserted-by":"crossref","unstructured":"Wang, Y., Sun, J., Bai, J., Anitescu, C., Eshaghi, M. S., Zhuang, X., Rabczuk, T., & Liu, Y. (2024). Kolmogorov Arnold Informed neural network: A physics-informed deep learning framework for solving PDEs based on Kolmogorov Arnold Networks, arXiv: 2406.11045.","DOI":"10.2139\/ssrn.4868150"},{"key":"10.1016\/j.neunet.2026.108888_bib0044","unstructured":"Yang, X., & Wang, X. (2024). Kolmogorov-Arnold transformer. arXiv: 2409.10594."},{"key":"10.1016\/j.neunet.2026.108888_bib0045","article-title":"Compressible non-Newtonian fluid based road traffic flow equation solved by physical-Informed rational neural network","author":"Yang","year":"2024","journal-title":"IEEE Access"},{"key":"10.1016\/j.neunet.2026.108888_bib0046","unstructured":"Zhangyanbo (2024). MLP-KAN. https:\/\/github.com\/Zhangyanbo\/MLP-KAN."}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003497?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026003497?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T02:56:38Z","timestamp":1781146598000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026003497"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":46,"alternative-id":["S0893608026003497"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108888","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"rKAN: Rational Kolmogorov-Arnold networks","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.108888","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108888"}}