{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T01:17:27Z","timestamp":1773796647468,"version":"3.50.1"},"reference-count":209,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001381","name":"National Research Foundation Singapore","doi-asserted-by":"publisher","award":["AISG3-TC-2024-014-SGKR"],"award-info":[{"award-number":["AISG3-TC-2024-014-SGKR"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]},{"name":"DSO National Laboratories","award":["AISG2-GC-2023-010"],"award-info":[{"award-number":["AISG2-GC-2023-010"]}]},{"name":"Anusandhan National Research Foundation","award":["RJF\/2022\/000115"],"award-info":[{"award-number":["RJF\/2022\/000115"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Comput. Intell. Mag."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/mci.2025.3607749","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T20:39:48Z","timestamp":1768423188000},"page":"16-36","source":"Crossref","is-referenced-by-count":2,"title":["Evolutionary Optimization of Physics-Informed Neural Networks: Evo-PINN Frontiers and Opportunities"],"prefix":"10.1109","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3215-1888","authenticated-orcid":false,"given":"Jian Cheng","family":"Wong","sequence":"first","affiliation":[{"name":"Agency for Science, Technology, Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6080-855X","authenticated-orcid":false,"given":"Abhishek","family":"Gupta","sequence":"additional","affiliation":[{"name":"Indian Institute of Technology (IIT) Goa, Ponda, India"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4813-4529","authenticated-orcid":false,"given":"Chin Chun","family":"Ooi","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology, Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5626-9688","authenticated-orcid":false,"given":"Pao-Hsiung","family":"Chiu","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology, Research (A*STAR), Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-3690-7923","authenticated-orcid":false,"given":"Jiao","family":"Liu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-169X","authenticated-orcid":false,"given":"Yew-Soon","family":"Ong","sequence":"additional","affiliation":[{"name":"Agency for Science, Technology, Research (A*STAR), Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1103\/RevModPhys.91.045002"},{"key":"ref2","article-title":"LLM2TEA: Agentic AI designer finds innovative objects with generative evolutionary multitasking","author":"Wong","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2414074122"},{"key":"ref4","article-title":"The AI scientist: Towards fully automated open-ended scientific discovery","author":"Lu","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/728"},{"key":"ref6","article-title":"Precise-physics driven text-to-3d generation","author":"Xu","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1115\/1.4064228"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11630-022-1564-2"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26093"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11081-023-09857-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijimpeng.2013.10.004"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1115\/1.4043587"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijfatigue.2021.106535"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1115\/1.4049861"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.tws.2024.112796"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2024.3452203"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1364\/BOE.432786"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1088\/0029-5515\/50\/4\/043002"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1088\/1741-4326\/ad6e9f"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.113959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2976199"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3301275.3308446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2928344"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2017.2720168"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3514228"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-021-00314-5"},{"key":"ref28","first-page":"2990","article-title":"Group equivariant convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Cohen","year":"2016"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1364\/OPTICA.6.000921"},{"key":"ref30","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2018.10.045"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(90)90007-N"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/72.712178"},{"key":"ref34","article-title":"JAX: Composable transformations of Python NumPy programs","author":"Bradbury","year":"2018"},{"key":"ref35","article-title":"Nvidia physicsnemo: An open-source framework for physics-based deep learning in science and engineering","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113552"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1137\/19m1274067"},{"key":"ref38","first-page":"26548","article-title":"Characterizing possible failure modes in physics-informed neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Krishnapriyan","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1615\/JMachLearnModelComput.2020033905"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jpca.1c05102"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s10915-022-01939-z"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s10409-021-01148-1"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3689037"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2442"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s44379-025-00015-1"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2025.117914"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/20M1318043"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2021.3061854"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00181"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110646"},{"key":"ref51","first-page":"7264","article-title":"Mitigating propagation failures in physics-informed neural networks using retain-resample-release (R3) sampling","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Daw","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tevc.2026.3650792"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.114909"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN54540.2023.10191236"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1017\/S0962492904000261"},{"key":"ref56","volume-title":"Navier\u2013Stokes Equations: Theory and Numerical Analysis","volume":"343","author":"Temam","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4020-3286-8_127"},{"key":"ref58","article-title":"Learning incompressible fluid dynamics from scratch\u2013towards fast, differentiable fluid models that generalize","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Wandel","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2020.113226"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-91518-3"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109913"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11831-021-09539-0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1029\/2019WR026731"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-26434-1"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-021-00158-0"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i1.16132"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3140726"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaw4741"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s00466-020-01952-9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.104902"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2100697118"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s00366-022-01709-3"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1137\/21M1397908"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2963375"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.113938"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2021.110768"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3530911"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.05.015"},{"key":"ref79","first-page":"8278","article-title":"Is $\\mathcal {L}^{2}$L2 physics-informed loss always suitable for training physics-informed neural network?","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"35","author":"Wang","year":"2022"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2024.116813"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TAI.2022.3192362"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.taml.2024.100515"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.107887"},{"key":"ref84","first-page":"5301","article-title":"On the spectral bias of neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Rahaman","year":"2019"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-36708-4_22"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1324"},{"key":"ref87","article-title":"Rethinking the importance of sampling in physics-informed neural networks","author":"Daw","year":"2022"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111855"},{"issue":"1","key":"ref89","article-title":"On the role of fixed points of dynamical systems in training physics-informed neural networks","volume":"2023","author":"Rohrhofer","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref90","article-title":"Pinnacle: PINN adaptive collocation and experimental points selection","volume-title":"Proc. Int. Conf. Mach. Learn. AI Sci. Workshop","author":"Lau","year":"2024"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650694"},{"key":"ref92","first-page":"110494","article-title":"ROPINN: Region optimized physics-informed neural networks","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"37","author":"Wu","year":"2024"},{"key":"ref93","article-title":"An Expert\u2019s guide to training physics-informed neural networks","author":"Wang","year":"2023"},{"issue":"402","key":"ref94","first-page":"1","article-title":"Piratenets: Physics-informed deep learning with residual adaptive networks","volume-title":"J. Mach. Learn. Res.","volume":"25","author":"Wang","year":"2024"},{"key":"ref95","article-title":"Gradient alignment in physics-informed neural networks: A second-order optimization perspective","author":"Wang","year":"2025"},{"key":"ref96","first-page":"7462","article-title":"Implicit neural representations with periodic activation functions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sitzmann","year":"2020"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2019.109136"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111232"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25988"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2021.104195"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.118852"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.4.023155"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111731"},{"key":"ref104","article-title":"Meta-learning of physics-informed neural networks for efficiently solving newly given PDES","author":"Iwata","year":"2023"},{"key":"ref105","article-title":"HyperPINN: Learning parameterized differential equations with physics-informed hypernetworks","volume-title":"The Symbiosis Deep Learn. Differ. Equ.","author":"Belbute-Peres","year":"2021"},{"key":"ref106","first-page":"23426","article-title":"Meta-auto-decoder for solving parametric partial differential equations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang","year":"2022"},{"key":"ref107","article-title":"Dats: Difficulty-aware task sampler for meta-learning physics-informed neural networks","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Toloubidokhti","year":"2023"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07294-2"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.111912"},{"key":"ref110","first-page":"11219-11231","article-title":"Hypernetwork-based meta-learning for low-rank physics-informed neural networks","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Cho","year":"2024"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.finel.2023.104047"},{"key":"ref112","first-page":"8510","article-title":"Parameterized physics-informed neural networks for parameterized PDES","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Cho","year":"2024"},{"key":"ref113","first-page":"1126","article-title":"Model-agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn","year":"2017"},{"key":"ref114","article-title":"Reptile: A scalable metalearning algorithm","author":"Nichol","year":"2018"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-024-00897-5"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1093\/imamat\/hxae011"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00278-8"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780195099713.001.0001"},{"issue":"18","key":"ref119","first-page":"1","article-title":"Information-geometric optimization algorithms: A unifying picture via invariance principles","volume":"18","author":"Ollivier","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref120","article-title":"PSO-PINN: Physics-informed neural networks trained with particle swarm optimization","author":"Davi","year":"2022"},{"key":"ref121","article-title":"Multi-objective PSO-PINN","volume-title":"Proc. 1st Workshop Synergy Sci. Mach. Learn. Model.","author":"Davi","year":"2023"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1098\/rspa.2021.0904"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2023.3277769"},{"key":"ref124","article-title":"How to select physics-informed neural networks in the absence of ground truth: A pareto front-based strategy","volume-title":"Proc. 1st Workshop Synergy Sci. Mach. Learn. Model.","author":"Wei","year":"2023"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3302892"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112211"},{"key":"ref127","volume-title":"Evolutionary Algorithms for Solving Multi-Objective Problems","author":"Coello","year":"2007"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.3390\/mca28050100"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.3390\/a16040194"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/4235.996017"},{"key":"ref131","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3529071"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2022.3144880"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2005.856143"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3061630"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.06.036"},{"key":"ref137","first-page":"6051","article-title":"Evolutionary stochastic gradient descent for optimization of deep neural networks","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Cui","year":"2018"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2011.2132725"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02729-2"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1145\/3712256.3726318"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1145\/3583133.3596397"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1162\/106365601750190398"},{"issue":"1","key":"ref143","first-page":"949","article-title":"Natural evolution strategies","volume":"15","author":"Wierstra","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.1.1"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3528770"},{"key":"ref146","article-title":"Evolution strategies as a scalable alternative to reinforcement learning","author":"Salimans","year":"2017"},{"key":"ref147","article-title":"Heuristically adaptive diffusion-model evolutionary strategy","author":"Hartl","year":"2024"},{"key":"ref148","article-title":"On empirical comparisons of optimizers for deep learning","author":"Choi","year":"2019"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3520304.3533983"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1145\/3205455.3205467"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3698203"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/s10208-015-9296-2"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3130838"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112603"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1016\/j.tws.2024.111693"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1177\/14750902231166424"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1080\/00295639.2023.2184194"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3100554"},{"key":"ref160","first-page":"980","article-title":"Automating discovery of physics-informed neural state space models via learning and evolution","volume-title":"Proc. Conf. Learn. Dyn. Control","author":"Skomski","year":"2021"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2024.101589"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.114129"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111290"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008202821328"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2018.2869001"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2017.2710978"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3126341"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2675628"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2809430"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2869674"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3064676"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1016\/j.tafmec.2019.102447"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2021.114474"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2022.113101"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-43325-1"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.3390\/app14083204"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI51031.2022.10022281"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2022.115852"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.109942"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2023.112291"},{"key":"ref181","first-page":"8803","article-title":"Loss surfaces, mode connectivity, and fast ensembling of DNNs","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Garipov","year":"2018"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2022.3155332"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2022.3221805"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1162\/978-0-262-31050-5-ch006"},{"key":"ref185","article-title":"L-hydra: Multi-head physics-informed neural networks","author":"Zou","year":"2023"},{"key":"ref186","article-title":"One-shot transfer learning of physics-informed neural networks","author":"Desai","year":"2021"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111121"},{"issue":"14","key":"ref188","first-page":"1","article-title":"Improving physics-informed neural networks with meta-learned optimization","volume":"25","author":"Bihlo","year":"2024","journal-title":"J. Mach. Learn. Res."},{"key":"ref189","first-page":"10553","article-title":"Unbiased gradient estimation in unrolled computation graphs with persistent evolution strategies","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Vicol","year":"2021"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36644-4_6"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1038\/s42254-024-00712-5"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650596"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00302-5"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1145\/3648506"},{"issue":"388","key":"ref195","first-page":"1","article-title":"Fourier neural operator with learned deformations for PDEs on general geometries","volume":"24","author":"Li","year":"2023","journal-title":"J. Mach. Learn. Res."},{"issue":"89","key":"ref196","first-page":"1","article-title":"Neural operator: Learning maps between function spaces with applications to PDEs","volume":"24","author":"Kovachki","year":"2023","journal-title":"J. Mach. Learn. Res."},{"key":"ref197","first-page":"12556","article-title":"GNOT: A general neural operator transformer for operator learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hao","year":"2023"},{"key":"ref198","first-page":"35836","article-title":"Geometry-informed neural operator for large-scale 3D PDEs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Li","year":"2023"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.abi8605"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2024.113433"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101805"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1126\/science.1165893"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1145\/3735634"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i18.30050"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8132-8_22"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i13.33556"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1137\/M1124176"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1016\/j.taml.2024.100563"},{"key":"ref209","article-title":"Evolutionary algorithms as an alternative to backpropagation for supervised training of biophysical neural networks and neural ODEs","author":"Hazelden","year":"2023"}],"container-title":["IEEE Computational Intelligence Magazine"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10207\/11353090\/11353124.pdf?arnumber=11353124","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T20:49:10Z","timestamp":1768596550000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11353124\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":209,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/mci.2025.3607749","relation":{},"ISSN":["1556-603X","1556-6048"],"issn-type":[{"value":"1556-603X","type":"print"},{"value":"1556-6048","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}