{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T16:16:13Z","timestamp":1787328973017,"version":"build-2736575974"},"reference-count":54,"publisher":"Society for Industrial & Applied Mathematics (SIAM)","issue":"3","funder":[{"name":"DARPA and SRC"},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0023191"],"award-info":[{"award-number":["DE-SC0023191"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ONR Vannevar Bush Faculty Fellowship","award":["N00014-22-1-2795"],"award-info":[{"award-number":["N00014-22-1-2795"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["SIAM J. Sci. Comput."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:p>Abstract.<\/jats:p>\n                  <jats:p>We introduce a method to convert physics-informed neural networks (PINNs), commonly used in scientific machine learning, to spiking neural networks (SNNs), which are expected to have higher energy efficiency compared to traditional artificial neural networks (ANNs). We first extend the calibration technique of SNNs to arbitrary activation functions beyond ReLU, making it more versatile, and we prove a theorem that ensures the effectiveness of the calibration. We successfully convert PINNs to SNNs, enabling computational efficiency for diverse regression tasks in solving multiple differential equations, including the unsteady Navier\u2013Stokes equations. We demonstrate great gains in terms of overall efficiency, including separable PINNs (SPINNs), which accelerate the training process. Overall, this is the first work of this kind and the proposed method achieves relatively good accuracy with low spike rates.<\/jats:p>","DOI":"10.1137\/24m1643232","type":"journal-article","created":{"date-parts":[[2025,5,2]],"date-time":"2025-05-02T06:54:15Z","timestamp":1746168855000},"page":"C559-C577","source":"Crossref","is-referenced-by-count":3,"title":["Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning"],"prefix":"10.1137","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4652-0699","authenticated-orcid":false,"given":"Qian","family":"Zhang","sequence":"first","affiliation":[{"name":"Division of Applied Mathematics, Brown University, Providence, RI 02912 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6099-126X","authenticated-orcid":true,"given":"Chenxi","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Engineering, Brown University, Providence, RI 02912 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4889-5037","authenticated-orcid":true,"given":"Adar","family":"Kahana","sequence":"additional","affiliation":[{"name":"Division of Applied Mathematics, Brown University, Providence, RI 02912 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9713-7120","authenticated-orcid":true,"given":"George Em","family":"Karniadakis","sequence":"additional","affiliation":[{"name":"Division of Applied Mathematics, Brown University, Providence, RI 02912 USA."},{"name":"School of Engineering, Brown University, Providence, RI 02912 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youngeun","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Yale University, New Haven, CT 06511 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuhang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Yale University, New Haven, CT 06511 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Priyadarshini","family":"Panda","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Yale University, New Haven, CT 06511 USA."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"351","published-online":{"date-parts":[[2025,5,2]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10409-021-01148-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.compstruc.2023.107228"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.08.017"},{"key":"ref4","unstructured":"E. Zhang, A. Kahana, A. Kopani\u010d\u00e1kov\u00e1, E. Turkel, R. Ranade, J. Pathak, and G. E. Karniadakis, Blending Neural Operators and Relaxation Methods in PDE Numerical Solvers, preprint, 2024, https:\/\/arxiv.org\/abs\/2208.13273v2."},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2023.116674"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00844-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-0716-3008-2_4"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1115\/1.4056566"},{"key":"ref9","volume":"11","author":"Zhang Q.","year":"2022","journal-title":"Trans. Vision Sci. Technol."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2024.110392"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2023.116300"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1009334"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00158-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1137\/19M1274067"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.115671"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.116805"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.114823"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2025.113947"},{"key":"ref20","first-page":"1","author":"Fan B.","year":"2024","journal-title":"Comput. Econom."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abk0644"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4741"},{"key":"ref23","unstructured":"E. Zhang, M. Yin, and G. E. Karniadakis, Physics-Informed Neural Networks for Nonhomogeneous Material Identification in Elasticity Imaging, preprint, arXiv:2009.04525, 2020."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1364\/OE.384875"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1137\/22M1518189"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111902"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.02-01-00032.1982"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1952.sp004716"},{"key":"ref29","volume-title":"Dynamical Systems in Neuroscience","author":"Izhikevich E. M.","year":"2007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511815706"},{"key":"ref31","doi-asserted-by":"crossref","unstructured":"R. Massa, A. Marchisio, M. Martina, and M. Shafique, An efficient spiking neural network for recognizing gestures with a DVS camera on the Loihi neuromorphic processor, in 2020 International Joint Conference on Neural Networks (IJCNN), IEEE, 2020, pp. 1\u20139.","DOI":"10.1109\/IJCNN48605.2020.9207109"},{"key":"ref32","doi-asserted-by":"crossref","unstructured":"Y. Kim, H. Park, A. Moitra, A. Bhattacharjee, Y. Venkatesha, and P. Panda, Rate coding or direct coding: Which one is better for accurate, robust, and energy-efficient spiking neural networks? in ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), IEEE, 2022, pp. 71\u201375.","DOI":"10.1109\/ICASSP43922.2022.9747906"},{"key":"ref33","first-page":"22","volume":"15","author":"Bouvier M.","year":"2019","journal-title":"ACM J. Emerg. Technol. Comput. Syst. (JETC)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1677-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.112130359"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SiPS52927.2021.00053"},{"key":"ref37","unstructured":"A. Kahana, Q. Zhang, L. Gleyzer, and G. E. Karniadakis, Spiking Neural Operators for Scientific Machine Learning, preprint, 2022, https:\/\/doi.org\/10.48550\/arXiv.2205.10130."},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2024.113363"},{"key":"ref39","doi-asserted-by":"crossref","unstructured":"J. M. Nageswaran, N. Dutt, Y. Wang, and T. Delbrueck, Computing spike-based convolutions on GPUs, in 2009 IEEE International Symposium on Circuits and Systems (ISCAS), IEEE, 2009, pp. 1917\u20131920.","DOI":"10.1109\/ISCAS.2009.5118157"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/BF00199450"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1038\/s41583-020-0277-3"},{"key":"ref43","unstructured":"Y. Li, S. Deng, X. Dong, R. Gong, and S. Gu, A free lunch from ANN: Towards efficient, accurate spiking neural networks calibration, in Proceedings of the 38th International Conference on Machine Learning, PMLR 139, 2021, pp. 6316\u20136325."},{"key":"ref44","doi-asserted-by":"crossref","unstructured":"J. Cho, S. Nam, H. Yang, S.B. Yun, Y. Hong, and E. Park, Separable PINN: Mitigating the Curse of Dimensionality in Physics-Informed Neural Networks, preprint, arXiv:2211.08761, 2022.","DOI":"10.52202\/075280-1032"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2017.00682"},{"key":"ref46","doi-asserted-by":"crossref","unstructured":"J. Ding, Z. Yu, Y. Tian, and T. Huang, Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks, preprint, arXiv:2105.11654, 2021.","DOI":"10.24963\/ijcai.2021\/321"},{"key":"ref47","doi-asserted-by":"crossref","unstructured":"Z. Hao, T. Bu, J. Ding, T. Huang, and Z. Yu, Reducing ann-snn conversion error through residual membrane potential, in Proceedings of the AAAI conference on artificial intelligence, vol. 37, 2023, pp. 11\u201321.","DOI":"10.1609\/aaai.v37i1.25071"},{"key":"ref48","unstructured":"B. Rueckauer, I.A. Lungu, Y. Hu, M. Pfeiffer, and S.C. Liu, Spiking Neural Network Conversion Toolbox, 2017, https:\/\/github.com\/NeuromorphicProcessorProject\/snn_toolbox."},{"key":"ref49","unstructured":"Y. Li, S. Deng, X. Dong, and S. Gu, Converting Artificial Neural Networks to Spiking Neural Networks via Parameter Calibration, preprint, https:\/\/arxiv.org\/abs\/2205.10121, 2022."},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2022.06.036"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109951"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1038\/s42005-024-01521-z"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2023.116064"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(85)90148-2"}],"container-title":["SIAM Journal on Scientific Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/epubs.siam.org\/doi\/pdf\/10.1137\/24M1643232","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,21]],"date-time":"2026-08-21T15:08:17Z","timestamp":1787324897000},"score":1,"resource":{"primary":{"URL":"https:\/\/epubs.siam.org\/doi\/10.1137\/24M1643232"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,2]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6,30]]}},"alternative-id":["10.1137\/24M1643232"],"URL":"https:\/\/doi.org\/10.1137\/24m1643232","relation":{},"ISSN":["1064-8275","1095-7197"],"issn-type":[{"value":"1064-8275","type":"print"},{"value":"1095-7197","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,2]]}}}