{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T13:53:18Z","timestamp":1775915598650,"version":"3.50.1"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"4-5","license":[{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T00:00:00Z","timestamp":1692230400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Swiss Federal Institute of Technology Zurich"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Biol Cybern"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The ability to sequentially learn multiple tasks without forgetting is a key skill of biological brains, whereas it represents a major challenge to the field of deep learning. To avoid catastrophic forgetting, various continual learning (CL) approaches have been devised. However, these usually require discrete task boundaries. This requirement seems biologically implausible and often limits the application of CL methods in the real world where tasks are not always well defined. Here, we take inspiration from neuroscience, where sparse, non-overlapping neuronal representations have been suggested to prevent catastrophic forgetting. As in the brain, we argue that these sparse representations should be chosen on the basis of feed forward (stimulus-specific) as well as top-down (context-specific) information. To implement such selective sparsity, we use a bio-plausible form of hierarchical credit assignment known as Deep Feedback Control (DFC) and combine it with a winner-take-all sparsity mechanism. In addition to sparsity, we introduce lateral recurrent connections within each layer to further protect previously learned representations. We evaluate the new sparse-recurrent version of DFC on the split-MNIST computer vision benchmark and show that only the combination of sparsity and intra-layer recurrent connections improves CL performance with respect to standard backpropagation. Our method achieves similar performance to well-known CL methods, such as Elastic Weight Consolidation and Synaptic Intelligence, without requiring information about task boundaries. Overall, we showcase the idea of adopting computational principles from the brain to derive new, task-free learning algorithms for CL.<\/jats:p>","DOI":"10.1007\/s00422-023-00973-w","type":"journal-article","created":{"date-parts":[[2023,8,17]],"date-time":"2023-08-17T09:02:36Z","timestamp":1692262956000},"page":"345-361","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Bio-inspired, task-free continual learning through activity regularization"],"prefix":"10.1007","volume":"117","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9535-9849","authenticated-orcid":false,"given":"Francesco","family":"L\u00e4ssig","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1218-4009","authenticated-orcid":false,"given":"Pau Vilimelis","family":"Aceituno","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0182-7443","authenticated-orcid":false,"given":"Martino","family":"Sorbaro","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8560-2120","authenticated-orcid":false,"given":"Benjamin F.","family":"Grewe","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,17]]},"reference":[{"key":"973_CR1","doi-asserted-by":"crossref","unstructured":"Aljundi R, Kelchtermans K, Tuytelaars T (2019) Task-free continual learning. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 11254\u201311263","DOI":"10.1109\/CVPR.2019.01151"},{"key":"973_CR2","unstructured":"Aljundi R, Lin M, Goujaud B, Bengio Y (2019) Gradient based sample selection for online continual learning. Adv Neural Inf Process Syst 32"},{"key":"973_CR3","first-page":"14387","volume":"33","author":"L Duncker","year":"2020","unstructured":"Duncker L, Driscoll L, Shenoy KV, Sahani M, Sussillo D (2020) Organizing recurrent network dynamics by task-computation to enable continual learning. Adv Neural Inf Process Syst 33:14387\u201314397","journal-title":"Adv Neural Inf Process Syst"},{"key":"973_CR4","unstructured":"French RM (1991) Using semi-distributed representations to overcome catastrophic forgetting in connectionist networks. In: Proceedings of the 13th annual cognitive science society conference, vol 1, pp. 173\u2013178"},{"issue":"8","key":"973_CR5","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"973_CR6","unstructured":"Hsu Y-C, Liu Y-C, Ramasamy A, Kira Z (2018) Re-evaluating continual learning scenarios: a categorization and case for strong baselines. arXiv preprint arXiv:1810.12488"},{"key":"973_CR7","doi-asserted-by":"crossref","unstructured":"Jedlicka P, Tomko M, Robins A, Abraham WC (2022) Contributions by metaplasticity to solving the catastrophic forgetting problem. Trends Neurosci","DOI":"10.1016\/j.tins.2022.06.002"},{"issue":"13","key":"973_CR8","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick J, Pascanu R, Rabinowitz N, Veness J, Desjardins G, Rusu AA, Milan K, Quan J, Ramalho T, Grabska-Barwinska A et al (2017) Overcoming catastrophic forgetting in neural networks. Proc Natl Acad Sci 114(13):3521\u20133526","journal-title":"Proc Natl Acad Sci"},{"issue":"3","key":"973_CR9","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/s42256-022-00452-0","volume":"4","author":"D Kudithipudi","year":"2022","unstructured":"Kudithipudi D, Aguilar-Simon M, Babb J, Bazhenov M, Blackiston D, Bongard J, Brna AP, Raja SC, Cheney N, Clune J et al (2022) Biological underpinnings for lifelong learning machines. Nat Mach Intell 4(3):196\u2013210","journal-title":"Nat Mach Intell"},{"key":"973_CR10","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22768-y","author":"A Laborieux","year":"2021","unstructured":"Laborieux A, Ernoult M, Hirtzlin T, Querlioz D (2021) Synaptic metaplasticity in binarized neural networks. Nat Commun. https:\/\/doi.org\/10.1038\/s41467-021-22768-y","journal-title":"Nat Commun"},{"key":"973_CR11","unstructured":"Lee S, Ha J, Zhang D, Kim G (2020) A neural Dirichlet process mixture model for task-free continual learning. In: International conference on learning representations"},{"issue":"4","key":"973_CR12","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1037\/bne0000371","volume":"134","author":"M Levinson","year":"2020","unstructured":"Levinson M, Kolenda JP, Alexandrou GJ, Escanilla O, Cleland TA, Smith DM, Linster C (2020) Context-dependent odor learning requires the anterior olfactory nucleus. Behav Neurosci 134(4):332","journal-title":"Behav Neurosci"},{"issue":"4","key":"973_CR13","doi-asserted-by":"publisher","first-page":"559","DOI":"10.1038\/nn.3660","volume":"17","author":"AC Lin","year":"2014","unstructured":"Lin AC, Bygrave AM, De Calignon A, Lee T, Miesenb\u00f6ck G (2014) Sparse, decorrelated odor coding in the mushroom body enhances learned odor discrimination. Nat Neurosci 17(4):559\u2013568","journal-title":"Nat Neurosci"},{"issue":"3","key":"973_CR14","doi-asserted-by":"publisher","first-page":"233","DOI":"10.1007\/s11263-016-0911-8","volume":"120","author":"A Mahendran","year":"2016","unstructured":"Mahendran A, Vedaldi A (2016) Visualizing deep convolutional neural networks using natural pre-images. Int J Comput Vis 120(3):233\u2013255","journal-title":"Int J Comput Vis"},{"key":"973_CR15","unstructured":"Manneschi L, Lin AC, Vasilaki E (2021) Sparce: improved learning of reservoir computing systems through sparse representations. IEEE Trans Neural Netw Learn Syst"},{"issue":"44","key":"973_CR16","doi-asserted-by":"publisher","first-page":"E10467","DOI":"10.1073\/pnas.1803839115","volume":"115","author":"NY Masse","year":"2018","unstructured":"Masse NY, Grant GD, Freedman DJ (2018) Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization. Proc Natl Acad Sci 115(44):E10467\u2013E10475","journal-title":"Proc Natl Acad Sci"},{"key":"973_CR17","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","volume":"24","author":"McCloskey Michael","year":"1989","unstructured":"Michael McCloskey, Cohen Neal J (1989) Catastrophic interference in connectionist networks: the sequential learning problem. Psychol Learn Motivat 24:109\u2013165","journal-title":"Psychol Learn Motivat"},{"key":"973_CR18","first-page":"4674","volume":"34","author":"A Meulemans","year":"2021","unstructured":"Meulemans A, Farinha MT, Ordonez JG, Aceituno PV, Sacramento J, Grewe BF (2021) Credit assignment in neural networks through deep feedback control. Adv Neural Inf Process Syst 34:4674\u20134687","journal-title":"Adv Neural Inf Process Syst"},{"key":"973_CR19","unstructured":"Meulemans A, Farinha MT, Cervera MR, Sacramento J, Grewe BF (2022) Minimizing control for credit assignment with strong feedback. In: KC, Stefanie J, Le S, Csaba S, Gang N, Sivan S (eds) Proceedings of the 39th international conference on machine learning, vol 162 of Proceedings of machine learning research, pp 15458\u201315483. 17\u201323 PMLR"},{"key":"973_CR20","unstructured":"Morcos AS, Barrett DGT, Rabinowitz NC, Botvinick M (2018) On the importance of single directions for generalization. In: International conference on learning representations. https:\/\/openreview.net\/forum?id=r1iuQjxCZ"},{"key":"973_CR21","unstructured":"Parisi GI, Ji X, Wermter S (2018) On the role of neurogenesis in overcoming catastrophic forgetting. arXiv preprint arXiv:1811.02113"},{"key":"973_CR22","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.neunet.2019.01.012","volume":"113","author":"GI Parisi","year":"2019","unstructured":"Parisi GI, Kemker R, Part JL, Kanan C, Wermter S (2019) Continual lifelong learning with neural networks: a review. Neural Netw 113:54\u201371","journal-title":"Neural Netw"},{"key":"973_CR23","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"key":"973_CR24","doi-asserted-by":"crossref","unstructured":"Pourcel J, Vu N-S, French RM (2022) Online task-free continual learning with dynamic sparse distributed memory. In: European conference on computer vision. Springer, pp 739\u2013756","DOI":"10.1007\/978-3-031-19806-9_42"},{"key":"973_CR25","unstructured":"Rao D, Visin F, Rusu A, Pascanu R, Teh YW, Hadsell R (2019) Continual unsupervised representation learning. In: Advances in neural information processing systems, 32"},{"key":"973_CR26","unstructured":"Roy O, Vetterli M (2007) The effective rank: a measure of effective dimensionality. In: 2007 15th European signal processing conference. IEEE, pp 606\u2013610"},{"key":"973_CR27","unstructured":"Rusu AA, Rabinowitz NC, Desjardins G, Soyer H, Kirkpatrick J, Kavukcuoglu K, Pascanu R, Hadsell R (2016) Progressive neural networks. arXiv preprint arXiv:1606.04671"},{"key":"973_CR28","unstructured":"Shin H, Lee JK, Kim J, Kim J (2017) Continual learning with deep generative replay. Adv Neural Inf Process Syst 30"},{"key":"973_CR29","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1016\/j.conb.2020.11.009","volume":"65","author":"RS van Bergen","year":"2020","unstructured":"van Bergen RS, Kriegeskorte N (2020) Going in circles is the way forward: the role of recurrence in visual inference. Curr Opin Neurobiol 65:176\u2013193","journal-title":"Curr Opin Neurobiol"},{"key":"973_CR30","unstructured":"Van\u00a0de Ven GM, Tolias AS (2019) Three scenarios for continual learning. arXiv preprint arXiv:1904.07734"},{"issue":"1","key":"973_CR31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41467-020-17866-2","volume":"11","author":"GM van de Ven","year":"2020","unstructured":"van de Ven GM, Siegelmann HT, Tolias AS (2020) Brain-inspired replay for continual learning with artificial neural networks. Nat Commun 11(1):1\u201314","journal-title":"Nat Commun"},{"issue":"1\u20133","key":"973_CR32","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/S0303-2647(98)00070-7","volume":"48","author":"R Van Rullen","year":"1998","unstructured":"Van Rullen R, Gautrais J, Delorme A, Thorpe S (1998) Face processing using one spike per neurone. Biosystems 48(1\u20133):229\u2013239","journal-title":"Biosystems"},{"key":"973_CR33","unstructured":"von Oswald J, Henning C, Sacramento J, Grewe BF (2020) Continual learning with hypernetworks. In: International conference on learning representations. https:\/\/arxiv.org\/abs\/1906.00695"},{"key":"973_CR34","unstructured":"Wang Z, Shen L, Fang L, Suo Q, Duan T, Gao M (2022) Improving task-free continual learning by distributionally robust memory evolution. In: International conference on machine learning, pp 22985\u201322998. PMLR"},{"key":"973_CR35","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747"},{"key":"973_CR36","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: European conference on computer vision. Springer, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"issue":"8","key":"973_CR37","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1038\/s42256-019-0080-x","volume":"1","author":"G Zeng","year":"2019","unstructured":"Zeng G, Chen Y, Cui B, Shan Yu (2019) Continual learning of context-dependent processing in neural networks. Nat Mach Intell 1(8):364\u2013372","journal-title":"Nat Mach Intell"},{"key":"973_CR38","unstructured":"Zenke F, Poole B, Ganguli S (2017) Continual learning through synaptic intelligence. In: International conference on machine learning. PMLR, pp 3987\u20133995"}],"container-title":["Biological Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-023-00973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00422-023-00973-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00422-023-00973-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,25]],"date-time":"2023-10-25T04:03:40Z","timestamp":1698206620000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00422-023-00973-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,17]]},"references-count":38,"journal-issue":{"issue":"4-5","published-online":{"date-parts":[[2023,10]]}},"alternative-id":["973"],"URL":"https:\/\/doi.org\/10.1007\/s00422-023-00973-w","relation":{},"ISSN":["1432-0770"],"issn-type":[{"value":"1432-0770","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,8,17]]},"assertion":[{"value":"30 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 August 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}