{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T22:41:14Z","timestamp":1780526474940,"version":"3.54.1"},"reference-count":30,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T00:00:00Z","timestamp":1736899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0012447"],"award-info":[{"award-number":["DE-SC0012447"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Recent work has established an alternative to traditional multi-layer perceptron neural networks in the form of Kolmogorov-Arnold Networks (KAN). The general KAN framework uses learnable activation functions on the edges of the computational graph followed by summation on nodes. The learnable edge activation functions in the original implementation are basis spline functions (B-Spline). Here, we present a model in which learnable grids of B-Spline activation functions are replaced by grids of re-weighted sine functions (SineKAN). We evaluate numerical performance of our model on a benchmark vision task. We show that our model can perform better than or comparable to B-Spline KAN models and an alternative KAN implementation based on periodic cosine and sine functions representing a Fourier Series. Further, we show that SineKAN has numerical accuracy that could scale comparably to dense neural networks (DNNs). Compared to the two baseline KAN models, SineKAN achieves a substantial speed increase at all hidden layer sizes, batch sizes, and depths. Current advantage of DNNs due to hardware and software optimizations are discussed along with theoretical scaling. Additionally, properties of SineKAN compared to other KAN implementations and current limitations are also discussed.<\/jats:p>","DOI":"10.3389\/frai.2024.1462952","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:16:21Z","timestamp":1736921781000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["SineKAN: Kolmogorov-Arnold Networks using sinusoidal activation functions"],"prefix":"10.3389","volume":"7","author":[{"given":"Eric","family":"Reinhardt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh","family":"Ramakrishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sergei","family":"Gleyzer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,1,15]]},"reference":[{"key":"B1","article-title":"fKAN: fractional Kolmogorov-Arnold networks with trainable Jacobi basis functions","author":"Aghaei","year":"","journal-title":"arXiv preprint arXiv:2406.07456"},{"key":"B2","article-title":"rKAN: rational Kolmogorov-Arnold networks","author":"Aghaei","year":"","journal-title":"arXiv preprint arXiv:2406.14495"},{"key":"B3","article-title":"WAV-KAN: wavelet Kolmogorov-Arnold networks","author":"Bozorgasl","year":"2024","journal-title":"arXiv preprint arXiv:2405.12832"},{"key":"B4","doi-asserted-by":"publisher","first-page":"653","DOI":"10.1007\/s00365-009-9054-2","article-title":"On a constructive proof of Kolmogorov's superposition theorem","volume":"30","author":"Braun","year":"2009","journal-title":"Constr. Approxim"},{"key":"B5","unstructured":"Cao\n              H.\n            \n          \n          Efficient-kan\n          \n          2024"},{"key":"B6","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1109\/MSP.2012.2211477","article-title":"The mnist database of handwritten digit images for machine learning research","volume":"29","author":"Deng","year":"2012","journal-title":"IEEE Signal Process. Mag"},{"key":"B7","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1109\/ICNN.1988.23903","article-title":"\u201cThere exists a neural network that does not make avoidable mistakes,\u201d","author":"Gallant","year":"1988","journal-title":"IEEE International Conference on Neural Networks"},{"key":"B8","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"\u201cDeep residual learning for image recognition,\u201d","author":"He","year":"2015","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"B9","doi-asserted-by":"publisher","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 Netw"},{"key":"B10","first-page":"383","article-title":"On the representation of continuous functions of several variables as superpositions of continuous functions of a smaller number of variables","volume":"108","author":"Kolmogorov","year":"1956","journal-title":"Doklady Akademii Nauk"},{"key":"B11","first-page":"953","article-title":"\u201cOn the representation of continuous functions of many variables by superposition of continuous functions of one variable and addition,\u201d","volume-title":"Doklady Akademii Nauk","author":"Kolmogorov","year":"1957"},{"key":"B12","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","article-title":"Backpropagation applied to handwritten zip code recognition","volume":"1","author":"LeCun","year":"1989","journal-title":"Neural Comput"},{"key":"B13","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"Lecun","year":"1998","journal-title":"Proc. IEEE"},{"key":"B14","article-title":"Implicit neural representation as a differentiable surrogate for photon propagation in a monolithic neutrino detector","author":"Lei","year":"2022","journal-title":"arXiv preprint arXiv:2211.01505"},{"key":"B15","article-title":"Leveraging sinusoidal representation networks to predict fMRI signals from EEG","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2311.04234"},{"key":"B16","article-title":"Kan: Kolmogorov-Arnold networks","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2404.19756"},{"key":"B17","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"arXiv preprint arXiv:1711.05101"},{"key":"B18","article-title":"Guidance and control networks with periodic activation functions","author":"Origer","year":"2024","journal-title":"arXiv preprint arXiv:2405.18084"},{"key":"B19","article-title":"\u201cTaming the waves: Sine as activation function in deep neural networks,\u201d","author":"Parascandolo","year":"2016","journal-title":"ICLR 2017"},{"key":"B20","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1038\/323533a0","article-title":"Learning representations by back-propagating errors","volume":"323","author":"Rumelhart","year":"","journal-title":"Nature"},{"key":"B21","volume-title":"Parallel Distributed Processing: Explorations in the Microstructure of Cognition, vol. 1: Foundations","author":"Rumelhart","year":""},{"key":"B22","article-title":"A comprehensive and fair comparison between MLP and KAN representations for differential equations and operator networks","author":"Shukla","year":"2024","journal-title":"arXiv preprint arXiv:2406.02917"},{"key":"B23","article-title":"Chebyshev polynomial-based Kolmogorov-Arnold networks: an efficient architecture for nonlinear function approximation","author":"Sidharth","year":"2024","journal-title":"arXiv preprint arXiv:2405.07200"},{"key":"B24","first-page":"7462","article-title":"\u201cImplicit neural representations with periodic activation functions,\u201d","author":"Sitzmann","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1049\/cp:19991129","article-title":"\u201cNeural networks with periodic and monotonic activation functions: a comparative study in classification problems,\u201d","author":"Sopena","year":"1999","journal-title":"Proceedings of the ICANN."},{"key":"B26","article-title":"BSRBF-KAN: a combination of b-splines and radial basic functions in Kolmogorov-Arnold networks","author":"Ta","year":"2024","journal-title":"arXiv preprint arXiv:2406.11173"},{"key":"B27","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"CoRR, abs\/1706.03762"},{"key":"B28","doi-asserted-by":"crossref","first-page":"106","DOI":"10.1109\/ICPR.2002.1047806","article-title":"\u201cHandwritten digit recognition using multilayer feedforward neural networks with periodic and monotonic activation functions,\u201d","volume-title":"Object Recognition Supported by User Interaction for Service Robots","author":"Wong","year":"2002"},{"key":"B29","article-title":"Fourierkan-GCF: fourier Kolmogorov-Arnold network-an effective and efficient feature transformation for graph collaborative filtering","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv:2406.01034"},{"key":"B30","article-title":"Fourier neural networks: a comparative study","author":"Zhumekenov","year":"2019","journal-title":"arXiv preprint arXiv:1902.03011"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1462952\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T06:16:27Z","timestamp":1736921787000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1462952\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,15]]},"references-count":30,"alternative-id":["10.3389\/frai.2024.1462952"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1462952","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,15]]},"article-number":"1462952"}}