{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:53:02Z","timestamp":1781193182778,"version":"3.54.1"},"reference-count":75,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T00:00:00Z","timestamp":1700092800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"DOI":"10.1038\/s42256-023-00747-w","type":"journal-article","created":{"date-parts":[[2023,11,16]],"date-time":"2023-11-16T17:01:58Z","timestamp":1700154118000},"page":"1356-1368","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":82,"title":["Incorporating neuro-inspired adaptability for continual learning in artificial intelligence"],"prefix":"10.1038","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3869-8155","authenticated-orcid":false,"given":"Liyuan","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingxing","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingtian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Su","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2388","authenticated-orcid":false,"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7927-5976","authenticated-orcid":false,"given":"Yi","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,11,16]]},"reference":[{"key":"747_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Z. & Liu, B. Lifelong machine learning. (San Rafael: Morgan & Claypool Publishers, 2018).","DOI":"10.1007\/978-3-031-01581-6"},{"key":"747_CR2","doi-asserted-by":"crossref","unstructured":"Parisi, G. I., Kemker, R., Part, J. L., Kanan, C. & Wermter, S. Continual lifelong learning with neural networks: a review. Neural Netw. 113, 54\u201371 (2019).","DOI":"10.1016\/j.neunet.2019.01.012"},{"key":"747_CR3","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/s42256-022-00452-0","volume":"4","author":"D Kudithipudi","year":"2022","unstructured":"Kudithipudi, D. et al. Biological underpinnings for lifelong learning machines. Nat. Mach. Intell. 4, 196\u2013210 (2022).","journal-title":"Nat. Mach. Intell."},{"key":"747_CR4","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","volume":"24","author":"M McCloskey","year":"1989","unstructured":"McCloskey, M. & Cohen, N. J. Catastrophic interference in connectionist networks: the sequential learning problem. Psychol. Learn. Motiv. 24, 109\u2013165 (1989).","journal-title":"Psychol. Learn. Motiv."},{"key":"747_CR5","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1037\/0033-295X.102.3.419","volume":"102","author":"JL McClelland","year":"1995","unstructured":"McClelland, J. L., McNaughton, B. L. & O\u2019Reilly, R. C. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol. Rev. 102, 419 (1995).","journal-title":"Psychol. Rev."},{"key":"747_CR6","unstructured":"Wang, L., Zhang, X., Su, H. & Zhu, J. A comprehensive survey of continual learning: theory, method and application. Preprint at https:\/\/arxiv.org\/abs\/2302.00487 (2023)."},{"key":"747_CR7","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J. et al. Overcoming catastrophic forgetting in neural networks. Proc. Natl Acad. Sci. USA 114, 3521\u20133526 (2017).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"747_CR8","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M. & Tuytelaars, T. Memory aware synapses: learning what (not) to forget. In Proc. European Conference on Computer Vision 139\u2013154 (Springer, 2018).","DOI":"10.1007\/978-3-030-01219-9_9"},{"key":"747_CR9","unstructured":"Zenke, F., Poole, B. & Ganguli, S. Continual learning through synaptic intelligence. In Proc. International Conference on Machine Learning 3987\u20133995 (PMLR, 2017)."},{"key":"747_CR10","doi-asserted-by":"crossref","unstructured":"Chaudhry, A., Dokania, P. K., Ajanthan, T. & Torr, P. H. Riemannian walk for incremental learning: understanding forgetting and intransigence. In Proc. European Conference on Computer Vision 532\u2013547 (Springer, 2018).","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"747_CR11","unstructured":"Ritter, H., Botev, A. & Barber, D. Online structured laplace approximations for overcoming catastrophic forgetting. Adv. Neural Inf. Process. Syst. 31, 3742\u20133752 (2018)."},{"key":"747_CR12","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.-A., Kolesnikov, A., Sperl, G. & Lampert, C. H. iCaRL: incremental classifier and representation learning. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 2001\u20132010 (IEEE, 2017).","DOI":"10.1109\/CVPR.2017.587"},{"key":"747_CR13","unstructured":"Shin, H., Lee, J. K., Kim, J. & Kim, J. Continual learning with deep generative replay. Adv. Neural Inf. Process. Syst. 30, 2990\u20132999 (2017)."},{"key":"747_CR14","unstructured":"Wang, L. et al. Memory replay with data compression for continual learning. In International Conference on Learning Representations (2021)."},{"key":"747_CR15","unstructured":"Serra, J., Suris, D., Miron, M. & Karatzoglou, A. Overcoming catastrophic forgetting with hard attention to the task. In Proc. International Conference on Machine Learning 4548\u20134557 (PMLR, 2018)."},{"key":"747_CR16","unstructured":"Fernando, C. et al. PathNet: evolution channels gradient descent in super neural networks. Preprint at https:\/\/arxiv.org\/abs\/1701.08734 (2017)."},{"key":"747_CR17","doi-asserted-by":"crossref","unstructured":"Delange, M. et al. A continual learning survey: defying forgetting in classification tasks. IEEE Trans. Pattern Anal. Mach. Intell. (2021).","DOI":"10.1109\/TPAMI.2021.3057446"},{"key":"747_CR18","doi-asserted-by":"publisher","first-page":"1028","DOI":"10.1016\/j.tics.2020.09.004","volume":"24","author":"R Hadsell","year":"2020","unstructured":"Hadsell, R., Rao, D., Rusu, A. A. & Pascanu, R. Embracing change: continual learning in deep neural networks. Trends Cogn. Sci. 24, 1028\u20131040 (2020).","journal-title":"Trends Cogn. Sci."},{"key":"747_CR19","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1016\/j.cell.2009.12.044","volume":"140","author":"Y Shuai","year":"2010","unstructured":"Shuai, Y. et al. Forgetting is regulated through Rac activity in Drosophila. Cell 140, 579\u2013589 (2010).","journal-title":"Cell"},{"key":"747_CR20","doi-asserted-by":"crossref","unstructured":"Cohn, R., Morantte, I. & Ruta, V. Coordinated and compartmentalized neuromodulation shapes sensory processing in Drosophila. Cell 163, 1742\u20131755 (2015).","DOI":"10.1016\/j.cell.2015.11.019"},{"key":"747_CR21","doi-asserted-by":"publisher","first-page":"R109","DOI":"10.1016\/j.cub.2015.12.023","volume":"26","author":"S Waddell","year":"2016","unstructured":"Waddell, S. Neural plasticity: dopamine tunes the mushroom body output network. Curr. Biol. 26, R109\u2013R112 (2016).","journal-title":"Curr. Biol."},{"key":"747_CR22","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1146\/annurev-neuro-080317-0621333","volume":"43","author":"MN Modi","year":"2020","unstructured":"Modi, M. N., Shuai, Y. & Turner, G. C. The Drosophila mushroom body: from architecture to algorithm in a learning circuit. Annu. Rev. Neurosci. 43, 465\u2013484 (2020).","journal-title":"Annu. Rev. Neurosci."},{"key":"747_CR23","doi-asserted-by":"publisher","first-page":"e04580","DOI":"10.7554\/eLife.04580","volume":"3","author":"Y Aso","year":"2014","unstructured":"Aso, Y. et al. Mushroom body output neurons encode valence and guide memory-based action selection in Drosophila. eLife 3, e04580 (2014).","journal-title":"eLife"},{"key":"747_CR24","doi-asserted-by":"publisher","first-page":"e16135","DOI":"10.7554\/eLife.16135","volume":"5","author":"Y Aso","year":"2016","unstructured":"Aso, Y. & Rubin, G. M. Dopaminergic neurons write and update memories with cell-type-specific rules. eLife 5, e16135 (2016).","journal-title":"eLife"},{"key":"747_CR25","doi-asserted-by":"publisher","first-page":"21191","DOI":"10.1073\/pnas.1903763116","volume":"116","author":"Y Gao","year":"2019","unstructured":"Gao, Y. et al. Genetic dissection of active forgetting in labile and consolidated memories in Drosophila. Proc. Natl Acad. Sci. USA 116, 21191\u201321197 (2019).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"747_CR26","doi-asserted-by":"crossref","unstructured":"Zhao, J. et al. Genetic dissection of mutual interference between two consecutive learning tasks in Drosophila. eLife 12, e83516 (2023).","DOI":"10.7554\/eLife.83516"},{"key":"747_CR27","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1016\/j.neuron.2017.04.037","volume":"94","author":"BA Richards","year":"2017","unstructured":"Richards, B. A. & Frankland, P. W. The persistence and transience of memory. Neuron 94, 1071\u20131084 (2017).","journal-title":"Neuron"},{"key":"747_CR28","doi-asserted-by":"publisher","first-page":"7644","DOI":"10.1073\/pnas.1602152113","volume":"113","author":"T Dong","year":"2016","unstructured":"Dong, T. et al. Inability to activate Rac1-dependent forgetting contributes to behavioral inflexibility in mutants of multiple autism-risk genes. Proc. Natl Acad. Sci. USA 113, 7644\u20137649 (2016).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"747_CR29","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1016\/j.neuron.2018.02.025","volume":"98","author":"X Zhang","year":"2018","unstructured":"Zhang, X., Li, Q., Wang, L., Liu, Z.-J. & Zhong, Y. Active protection: learning-activated Raf\/MAPK activity protects labile memory from Rac1-independent forgetting. Neuron 98, 142\u2013155 (2018).","journal-title":"Neuron"},{"key":"747_CR30","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.neuron.2017.05.039","volume":"95","author":"RL Davis","year":"2017","unstructured":"Davis, R. L. & Zhong, Y. The biology of forgetting\u2014a perspective. Neuron 95, 490\u2013503 (2017).","journal-title":"Neuron"},{"key":"747_CR31","doi-asserted-by":"crossref","unstructured":"Mo, H. et al. Age-related memory vulnerability to interfering stimuli is caused by gradual loss of MAPK-dependent protection in Drosophila. Aging Cell 21, e13628 (2022).","DOI":"10.1111\/acel.13628"},{"key":"747_CR32","doi-asserted-by":"publisher","first-page":"1230","DOI":"10.1016\/j.neuron.2016.05.010","volume":"90","author":"I Cervantes-Sandoval","year":"2016","unstructured":"Cervantes-Sandoval, I., Chakraborty, M., MacMullen, C. & Davis, R. L. Scribble scaffolds a signalosome for active forgetting. Neuron 90, 1230\u20131242 (2016).","journal-title":"Neuron"},{"key":"747_CR33","doi-asserted-by":"publisher","first-page":"3211","DOI":"10.1016\/j.neuron.2021.08.001","volume":"109","author":"NC Noyes","year":"2021","unstructured":"Noyes, N. C., Phan, A. & Davis, R. L. Memory suppressor genes: modulating acquisition, consolidation, and forgetting. Neuron 109, 3211\u20133227 (2021).","journal-title":"Neuron"},{"key":"747_CR34","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1016\/j.conb.2017.12.002","volume":"49","author":"P Cognigni","year":"2018","unstructured":"Cognigni, P., Felsenberg, J. & Waddell, S. Do the right thing: neural network mechanisms of memory formation, expression and update in Drosophila. Curr. Opin. Neurobiol. 49, 51\u201358 (2018).","journal-title":"Curr. Opin. Neurobiol."},{"key":"747_CR35","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.cois.2019.06.003","volume":"36","author":"H Amin","year":"2019","unstructured":"Amin, H. & Lin, A. C. Neuronal mechanisms underlying innate and learned olfactory processing in Drosophila. Curr. Opin. Insect Sci. 36, 9\u201317 (2019).","journal-title":"Curr. Opin. Insect Sci."},{"key":"747_CR36","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.cell.2019.05.040","volume":"178","author":"A Handler","year":"2019","unstructured":"Handler, A. et al. Distinct dopamine receptor pathways underlie the temporal sensitivity of associative learning. Cell 178, 60\u201375 (2019).","journal-title":"Cell"},{"key":"747_CR37","doi-asserted-by":"crossref","unstructured":"McCurdy, L. Y., Sareen, P., Davoudian, P. A. & Nitabach, M. N. Dopaminergic mechanism underlying reward-encoding of punishment omission during reversal learning in Drosophila. Nat. Commun. 12, 1115 (2021).","DOI":"10.1038\/s41467-021-21388-w"},{"key":"747_CR38","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1016\/j.neuron.2012.04.007","volume":"74","author":"JA Berry","year":"2012","unstructured":"Berry, J. A., Cervantes-Sandoval, I., Nicholas, E. P. & Davis, R. L. Dopamine is required for learning and forgetting in Drosophila. Neuron 74, 530\u2013542 (2012).","journal-title":"Neuron"},{"key":"747_CR39","doi-asserted-by":"publisher","first-page":"651","DOI":"10.1016\/j.celrep.2018.09.051","volume":"25","author":"JA Berry","year":"2018","unstructured":"Berry, J. A., Phan, A. & Davis, R. L. Dopamine neurons mediate learning and forgetting through bidirectional modulation of a memory trace. Cell Rep. 25, 651\u2013662 (2018).","journal-title":"Cell Rep."},{"key":"747_CR40","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1038\/s41593-021-00809-5","volume":"24","author":"L Aitchison","year":"2021","unstructured":"Aitchison, L. et al. Synaptic plasticity as bayesian inference. Nat. Neurosci. 24, 565\u2013571 (2021).","journal-title":"Nat. Neurosci."},{"key":"747_CR41","doi-asserted-by":"publisher","first-page":"e69884","DOI":"10.7554\/eLife.69884","volume":"10","author":"S Schug","year":"2021","unstructured":"Schug, S., Benzing, F. & Steger, A. Presynaptic stochasticity improves energy efficiency and helps alleviate the stability\u2013plasticity dilemma. eLife 10, e69884 (2021).","journal-title":"eLife"},{"key":"747_CR42","unstructured":"Wang, L. et al. AFEC: active forgetting of negative transfer in continual learning. Adv. Neural Inf. Process. Syst. 34, 22379\u201322391 (2021)."},{"key":"747_CR43","unstructured":"Benzing, F. Unifying importance based regularisation methods for continual learning. In Proc. International Conference on Artificial Intelligence and Statistics 2372\u20132396 (PMLR, 2022)."},{"key":"747_CR44","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1037\/0033-2909.114.1.80","volume":"114","author":"ME Bouton","year":"1993","unstructured":"Bouton, M. E. Context, time, and memory retrieval in the interference paradigms of pavlovian learning. Psychol. Bull. 114, 80 (1993).","journal-title":"Psychol. Bull."},{"key":"747_CR45","unstructured":"Krizhevsky, A. et al. Learning multiple layers of features from tiny images. Technical Report, Citeseer (2009)."},{"key":"747_CR46","doi-asserted-by":"crossref","unstructured":"Shuai, Y. et al. Dissecting neural pathways for forgetting in Drosophila olfactory aversive memory. Proc. Natl Acad. Sci. USA 112, E6663\u2013E6672 (2015).","DOI":"10.1073\/pnas.1512792112"},{"key":"747_CR47","unstructured":"Chen, L. et al. AI of brain and cognitive sciences: from the perspective of first principles. Preprint at https:\/\/arxiv.org\/abs\/2301.08382 (2023)."},{"key":"747_CR48","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1038\/nature12063","volume":"497","author":"SJ Caron","year":"2013","unstructured":"Caron, S. J., Ruta, V., Abbott, L. F. & Axel, R. Random convergence of olfactory inputs in the Drosophila mushroom body. Nature 497, 113\u2013117 (2013).","journal-title":"Nature"},{"key":"747_CR49","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.neuron.2020.07.029","volume":"108","author":"K Endo","year":"2020","unstructured":"Endo, K., Tsuchimoto, Y. & Kazama, H. Synthesis of conserved odor object representations in a random, divergent-convergent network. Neuron 108, 367\u2013381 (2020).","journal-title":"Neuron"},{"key":"747_CR50","unstructured":"Long, M., Cao, Y., Wang, J. & Jordan, M. Learning transferable features with deep adaptation networks. In Proc. International Conference on Machine Learning 97\u2013105 (PMLR, 2015)."},{"key":"747_CR51","doi-asserted-by":"crossref","unstructured":"Wang, L., Zhang, X., Li, Q., Zhu, J. & Zhong, Y. CoSCL: cooperation of small continual learners is stronger than a big one. In Proc. European Conference on Computer Vision 254\u2013271 (Springer, 2022).","DOI":"10.1007\/978-3-031-19809-0_15"},{"key":"747_CR52","doi-asserted-by":"crossref","unstructured":"van de Ven, G. M., Tuytelaars, T. & Tolias, A. S. Three types of incremental learning. Nat. Mach. Intell. 4, 1185\u20131197 (2022).","DOI":"10.1038\/s42256-022-00568-3"},{"key":"747_CR53","unstructured":"Riemer, M. et al. Learning to learn without forgetting by maximizing transfer and minimizing interference. In International Conference on Learning Representations (2018)."},{"key":"747_CR54","unstructured":"Schwarz, J. et al. Progress & compress: a scalable framework for continual learning. In Proc. International Conference on Machine Learning 4528\u20134537 (PMLR, 2018)."},{"key":"747_CR55","unstructured":"Jung, S., Ahn, H., Cha, S. & Moon, T. Continual learning with node-importance based adaptive group sparse regularization. Adv. Neural Inf. Process. Syst. 33, 3647\u20133658 (2020)."},{"key":"747_CR56","unstructured":"Cha, S., Hsu, H., Hwang, T., Calmon, F. & Moon, T. CPR: classifier-projection regularization for continual learning. In International Conference on Learning Representations (2020)."},{"key":"747_CR57","doi-asserted-by":"publisher","first-page":"1332","DOI":"10.1126\/science.aab3050","volume":"350","author":"BM Lake","year":"2015","unstructured":"Lake, B. M., Salakhutdinov, R. & Tenenbaum, J. B. Human-level concept learning through probabilistic program induction. Science 350, 1332\u20131338 (2015).","journal-title":"Science"},{"key":"747_CR58","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P. & Belongie, S. The Caltech-UCSD birds-200-2011 dataset. (2011). http:\/\/www.vision.caltech.edu\/datasets\/"},{"key":"747_CR59","unstructured":"Lomonaco, V. & Maltoni, D. Core50: a new dataset and benchmark for continuous object recognition. In Conference on Robot Learning 17\u201326 (PMLR, 2017)."},{"key":"747_CR60","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/s41583-021-00548-3","volume":"23","author":"TJ Ryan","year":"2022","unstructured":"Ryan, T. J. & Frankland, P. W. Forgetting as a form of adaptive engram cell plasticity. Nat. Rev. Neurosci. 23, 173\u2013186 (2022).","journal-title":"Nat. Rev. Neurosci."},{"key":"747_CR61","doi-asserted-by":"crossref","unstructured":"Luo, L. et al. Differential effects of the Rac GTPase on Purkinje cell axons and dendritic trunks and spines. Nature 379, 837\u2013840 (1996).","DOI":"10.1038\/379837a0"},{"key":"747_CR62","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1093\/cercor\/10.10.927","volume":"10","author":"A Tashiro","year":"2000","unstructured":"Tashiro, A., Minden, A. & Yuste, R. Regulation of dendritic spine morphology by the rho family of small gtpases: antagonistic roles of Rac and Rho. Cerebral Cortex 10, 927\u2013938 (2000).","journal-title":"Cerebral Cortex"},{"key":"747_CR63","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/nn.2487","volume":"13","author":"A Hayashi-Takagi","year":"2010","unstructured":"Hayashi-Takagi, A. et al. Disrupted-in-Schizophrenia 1 (DISC1) regulates spines of the glutamate synapse via Rac1. Nat. Neurosci. 13, 327\u2013332 (2010).","journal-title":"Nat. Neurosci."},{"key":"747_CR64","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/nature15257","volume":"525","author":"A Hayashi-Takagi","year":"2015","unstructured":"Hayashi-Takagi, A. et al. Labelling and optical erasure of synaptic memory traces in the motor cortex. Nature 525, 333\u2013338 (2015).","journal-title":"Nature"},{"key":"747_CR65","unstructured":"Martens, J. & Grosse, R. Optimizing neural networks with kronecker-factored approximate curvature. In Proc. International Conference on Machine Learning 2408\u20132417 (PMLR, 2015)."},{"key":"747_CR66","unstructured":"Knoblauch, J., Husain, H. & Diethe, T. Optimal continual learning has perfect memory and is NP-hard. In Proc. International Conference on Machine Learning 5327\u20135337 (PMLR, 2020)."},{"key":"747_CR67","unstructured":"Deng, D., Chen, G., Hao, J., Wang, Q. & Heng, P.-A. Flattening sharpness for dynamic gradient projection memory benefits continual learning. Adv. Neural Inf. Process. Syst. 34, 18710\u201318721 (2021)."},{"key":"747_CR68","first-page":"7308","volume":"33","author":"SI Mirzadeh","year":"2020","unstructured":"Mirzadeh, S. I., Farajtabar, M., Pascanu, R. & Ghasemzadeh, H. Understanding the role of training regimes in continual learning. Adv. Neural Inf. Process. Syst. 33, 7308\u20137320 (2020).","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"747_CR69","doi-asserted-by":"crossref","unstructured":"McAllester, D. A. PAC-Bayesian model averaging. In Proc. Twelfth Annual Conference on Computational Learning Theory 164\u2013170 (ACM, 1999).","DOI":"10.1145\/307400.307435"},{"key":"747_CR70","unstructured":"Pham, Q., Liu, C., Sahoo, D. & Steven, H. Contextual transformation networks for online continual learning. In International Conference on Learning Representations (2021)."},{"key":"747_CR71","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A. & Klimov, O. Proximal policy optimization algorithms. Preprint at https:\/\/arxiv.org\/abs\/1707.06347 (2017)."},{"key":"747_CR72","unstructured":"Lopez-Paz, D. et al. Gradient episodic memory for continual learning. Adv. Neural Inf. Process. Syst. 30, 6467\u20136476 (2017)."},{"key":"747_CR73","unstructured":"Mnih, V. et al. Playing Atari with deep reinforcement learning. Preprint at https:\/\/arxiv.org\/abs\/1312.5602 (2013)."},{"key":"747_CR74","doi-asserted-by":"publisher","unstructured":"Wang, L. & Zhang, X. lywang3081\/CAF: CAF paper. Zenodo https:\/\/doi.org\/10.5281\/zenodo.8293564 (2023).","DOI":"10.5281\/zenodo.8293564"},{"key":"747_CR75","doi-asserted-by":"crossref","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. In Proc. IEEE Conference on Computer Vision and Pattern Recognition 618\u2013626 (IEEE, 2017).","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00747-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00747-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00747-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,18]],"date-time":"2023-12-18T20:08:20Z","timestamp":1702930100000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00747-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,16]]},"references-count":75,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["747"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00747-w","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,16]]},"assertion":[{"value":"3 October 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 September 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 November 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}