{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T13:19:24Z","timestamp":1770815964306,"version":"3.50.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2025,11,6]],"date-time":"2025-11-06T00:00:00Z","timestamp":1762387200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003382","name":"Core Research for Evolutional Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR22P1"],"award-info":[{"award-number":["JPMJCR22P1"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP23wm0625001"],"award-info":[{"award-number":["JP23wm0625001"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002241","name":"Japan Science and Technology Agency","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002241","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP23H04973"],"award-info":[{"award-number":["JP23H04973"]}],"id":[{"id":"10.13039\/501100001691","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":[[2026,3]]},"DOI":"10.1016\/j.neunet.2025.108311","type":"journal-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T16:12:20Z","timestamp":1762618340000},"page":"108311","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Synaptic pruning facilitates online Bayesian model selection"],"prefix":"10.1016","volume":"195","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2763-7700","authenticated-orcid":false,"given":"Ukyo T.","family":"Tazawa","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2960-4919","authenticated-orcid":false,"given":"Takuya","family":"Isomura","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2025.108311_bib0001","series-title":"Pattern recognition and machine learning","author":"Bishop","year":"2006"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0002","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.bbr.2009.08.031","article-title":"Structure learning in action","volume":"206","author":"Braun","year":"2010","journal-title":"Behavioural Brain Research"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0003","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/S0166-2236(00)01683-0","article-title":"Independent component analysis at the neural cocktail party","volume":"24","author":"Brown","year":"2001","journal-title":"Trends in Neurosciences"},{"issue":"7","key":"10.1016\/j.neunet.2025.108311_bib0004","doi-asserted-by":"crossref","first-page":"1759","DOI":"10.1162\/089976698300017124","article-title":"Synaptic pruning in development: A computational account","volume":"10","author":"Chechik","year":"1998","journal-title":"Neural Computation"},{"key":"10.1016\/j.neunet.2025.108311_bib0005","first-page":"6","article-title":"Blind source separation and independent component analysis: A review","author":"Choi","year":"2004","journal-title":"Neural Information Processing - Letters and Reviews"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0006","doi-asserted-by":"crossref","first-page":"190","DOI":"10.1037\/a0030852","article-title":"Cognitive control over learning: Creating, clustering, and generalizing task-set structure","volume":"120","author":"Collins","year":"2013","journal-title":"Psychological Review"},{"issue":"6","key":"10.1016\/j.neunet.2025.108311_bib0007","doi-asserted-by":"crossref","first-page":"445","DOI":"10.1016\/S0006-3495(61)86902-6","article-title":"Impulses and physiological states in theoretical models of nerve membrane","volume":"1","author":"FitzHugh","year":"1961","journal-title":"Biophysical Journal"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0008","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1038\/nrn2787","article-title":"The free-energy principle: A unified brain theory?","volume":"11","author":"Friston","year":"2010","journal-title":"Nature Reviews Neuroscience"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0009","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1016\/j.jphysparis.2006.10.001","article-title":"A free energy principle for the brain","volume":"100","author":"Friston","year":"2006","journal-title":"Journal of Physiology-Paris"},{"key":"10.1016\/j.neunet.2025.108311_bib0010","unstructured":"Friston, K., Parr, T., & Zeidman, P. (2019). Bayesian model reduction. ArXiv preprint arXiv:1805.07092. https:\/\/doi.org\/10.48550\/arXiv.1805.07092."},{"key":"10.1016\/j.neunet.2025.108311_bib0011","doi-asserted-by":"crossref","DOI":"10.1016\/j.biopsycho.2024.108891","article-title":"Supervised structure learning","volume":"193","author":"Friston","year":"2024","journal-title":"Biological Psychology"},{"issue":"10","key":"10.1016\/j.neunet.2025.108311_bib0012","doi-asserted-by":"crossref","first-page":"2633","DOI":"10.1162\/neco_a_00999","article-title":"Active inference, curiosity and insight","volume":"29","author":"Friston","year":"2017","journal-title":"Neural Computation"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0013","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1016\/0925-2312(94)90055-8","article-title":"A simple and effective method for removal of hidden units and weights","volume":"6","author":"Hagiwara","year":"1994","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neunet.2025.108311_bib0014","unstructured":"Han, S., Mao, H., & Dally, W.J. (2016). Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149. https:\/\/doi.org\/10.48550\/arXiv.1510.00149."},{"key":"10.1016\/j.neunet.2025.108311_bib0015","unstructured":"Han, S., Pool, J., Tran, J., & Dally, W.J. (2015). Learning both weights and connections for efficient neural networks. arXiv preprint arXiv:1506.02626. https:\/\/doi.org\/10.48550\/arXiv.1506.02626."},{"key":"10.1016\/j.neunet.2025.108311_bib0016","series-title":"The organization of behavior: A neuropsychological theory","author":"Hebb","year":"1949"},{"key":"10.1016\/j.neunet.2025.108311_bib0017","doi-asserted-by":"crossref","DOI":"10.3389\/neuro.10.007.2008","article-title":"Structural plasticity controlled by calcium based correlation detection","volume":"2","author":"Helias","year":"2008","journal-title":"Frontiers in Computational Neuroscience"},{"issue":"4","key":"10.1016\/j.neunet.2025.108311_bib0018","doi-asserted-by":"crossref","first-page":"500","DOI":"10.1113\/jphysiol.1952.sp004764","article-title":"A quantitative description of membrane current and its application to conduction and excitation in nerve","volume":"117","author":"Hodgkin","year":"1952","journal-title":"The Journal of Physiology"},{"key":"10.1016\/j.neunet.2025.108311_bib0019","unstructured":"Hoefler, T., Alistarh, D., Ben-Nun, T., Dryden, N., & Peste, A. (2021). Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks. arXiv preprint arXiv: 2102.00554. https:\/\/doi.org\/10.48550\/arXiv.2102.00554."},{"issue":"11","key":"10.1016\/j.neunet.2025.108311_bib0020","doi-asserted-by":"crossref","first-page":"2085","DOI":"10.1162\/neco_a_01315","article-title":"Reverse-engineering neural networks to characterize their cost functions","volume":"32","author":"Isomura","year":"2020","journal-title":"Neural Computation"},{"issue":"12","key":"10.1016\/j.neunet.2025.108311_bib0021","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004643","article-title":"Cultured cortical neurons can perform blind source separation according to the free-energy principle","volume":"11","author":"Isomura","year":"2015","journal-title":"PLOS Computational Biology"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0022","doi-asserted-by":"crossref","first-page":"4547","DOI":"10.1038\/s41467-023-40141-z","article-title":"Experimental validation of the free-energy principle with in vitro neural networks","volume":"14","author":"Isomura","year":"2023","journal-title":"Nature Communications"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0023","doi-asserted-by":"crossref","DOI":"10.1038\/s42003-021-02994-2","article-title":"Canonical neural networks perform active inference","volume":"5","author":"Isomura","year":"2022","journal-title":"Communications Biology"},{"issue":"2160","key":"10.1016\/j.neunet.2025.108311_bib0024","article-title":"Structure learning in coupled dynamical systems and dynamic causal modelling","volume":"377","author":"Jafarian","year":"2019","journal-title":"Philosophical Transactions of the Royal Society A"},{"issue":"3","key":"10.1016\/j.neunet.2025.108311_bib0025","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1000022","article-title":"Structure of spontaneous UP and DOWN transitions self-organizing in a cortical network model","volume":"4","author":"Kang","year":"2008","journal-title":"PLOS Computational Biology"},{"issue":"7","key":"10.1016\/j.neunet.2025.108311_bib0026","doi-asserted-by":"crossref","first-page":"407","DOI":"10.1038\/s41583-021-00467-3","article-title":"Spine dynamics in the brain, mental disorders and artificial neural networks","volume":"22","author":"Kasai","year":"2021","journal-title":"Nature Reviews Neuroscience"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0027","doi-asserted-by":"crossref","first-page":"253","DOI":"10.1146\/annurev-control-042920-092451","article-title":"Partially observable Markov decision processes and robotics","volume":"5","author":"Kurniawati","year":"2022","journal-title":"Annual Review of Control, Robotics, and Autonomous Systems"},{"issue":"35","key":"10.1016\/j.neunet.2025.108311_bib0028","doi-asserted-by":"crossref","first-page":"13214","DOI":"10.1073\/pnas.0604691103","article-title":"Spontaneous and evoked synaptic rewiring in the neonatal neocortex","volume":"103","author":"Le B\u00e9","year":"2006","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"6","key":"10.1016\/j.neunet.2025.108311_bib0029","doi-asserted-by":"crossref","first-page":"545","DOI":"10.1038\/75714","article-title":"Synaptic plasticity and dynamic modulation of the postsynaptic membrane","volume":"3","author":"L\u00fcscher","year":"2000","journal-title":"Nature Neuroscience"},{"issue":"47","key":"10.1016\/j.neunet.2025.108311_bib0030","doi-asserted-by":"crossref","first-page":"29407","DOI":"10.1073\/pnas.1912328117","article-title":"How humans learn and represent networks","volume":"117","author":"Lynn","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0031","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.neuron.2004.09.012","article-title":"LTP and LTD: An embarrassment of riches","volume":"44","author":"Malenka","year":"2004","journal-title":"Neuron"},{"key":"10.1016\/j.neunet.2025.108311_bib0032","doi-asserted-by":"crossref","first-page":"88231","DOI":"10.1109\/ACCESS.2024.3417219","article-title":"Bayesian sparsification for deep neural networks with Bayesian model reduction","volume":"12","author":"Markovi\u0107","year":"2024","journal-title":"IEEE Access : Practical Innovations, Open Solutions"},{"issue":"10","key":"10.1016\/j.neunet.2025.108311_bib0033","doi-asserted-by":"crossref","first-page":"2061","DOI":"10.1109\/JRPROC.1962.288235","article-title":"An active pulse transmission line simulating nerve axon","volume":"50","author":"Nagumo","year":"1962","journal-title":"Proceedings of the IRE"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0034","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.neuron.2016.12.015","article-title":"A brief history of long-term potentiation","volume":"93","author":"Nicoll","year":"2017","journal-title":"Neuron"},{"issue":"28","key":"10.1016\/j.neunet.2025.108311_bib0035","doi-asserted-by":"crossref","first-page":"16096","DOI":"10.1073\/pnas.2010281117","article-title":"How synaptic pruning shapes neural wiring during development and, possibly, in disease","volume":"117","author":"Sakai","year":"2020","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0036","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/35039075","article-title":"Postsynaptic organisation and regulation of excitatory synapses","volume":"1","author":"Scannevin","year":"2000","journal-title":"Nature Reviews Neuroscience"},{"issue":"10","key":"10.1016\/j.neunet.2025.108311_bib0037","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1009458","article-title":"The information theory of developmental pruning: Optimizing global network architectures using local synaptic rules","volume":"17","author":"Scholl","year":"2021","journal-title":"PLOS Computational Biology"},{"issue":"1","key":"10.1016\/j.neunet.2025.108311_bib0038","doi-asserted-by":"crossref","first-page":"67","DOI":"10.1016\/0893-6080(91)90033-2","article-title":"Creating artificial neural networks that generalize","volume":"4","author":"Sietsma","year":"1991","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2025.108311_bib0039","unstructured":"Sun, Y., Wang, X., & Tang, X. (2015). Sparsifying neural network connections for face recognition. arXiv preprint arXiv: 1512.01891. https:\/\/doi.org\/10.48550\/arXiv.1512.01891."},{"issue":"6022","key":"10.1016\/j.neunet.2025.108311_bib0040","doi-asserted-by":"crossref","first-page":"1279","DOI":"10.1126\/science.1192788","article-title":"How to grow a mind: Statistics, structure, and abstraction","volume":"331","author":"Tenenbaum","year":"2011","journal-title":"Science (New York, N.Y.)"},{"key":"10.1016\/j.neunet.2025.108311_bib0041","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.conb.2016.01.014","article-title":"Toward the neural implementation of structure learning","volume":"37","author":"Tervo","year":"2016","journal-title":"Current Opinion in Neurobiology"},{"issue":"7","key":"10.1016\/j.neunet.2025.108311_bib0042","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pcbi.1004299","article-title":"Adaptive synaptogenesis constructs neural codes that benefit discrimination","volume":"11","author":"Thomas","year":"2015","journal-title":"PLOS Computational Biology"},{"issue":"2","key":"10.1016\/j.neunet.2025.108311_bib0043","doi-asserted-by":"crossref","first-page":"89","DOI":"10.1016\/j.tins.2017.12.003","article-title":"Synaptic tenacity or lack thereof: Spontaneous remodeling of synapses","volume":"41","author":"Ziv","year":"2018","journal-title":"Trends in Neurosciences"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802501192X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S089360802501192X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T10:12:29Z","timestamp":1770804749000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S089360802501192X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":43,"alternative-id":["S089360802501192X"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108311","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Synaptic pruning facilitates online Bayesian model selection","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2025.108311","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2025 The Author(s). Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"108311"}}