Embracing Change: Continual Learning in Deep Neural Networks
Open accessAbstract
Artificial intelligence research has seen enormous progress over the past few decades, but it predominantly relies on fixed datasets and stationary environments. Continual learning is an increasingly relevant area of study that asks how artificial systems might learn sequentially, as biological systems do, from a continuous stream of correlated data. In the present review, we relate continual learning to the learning dynamics of neural networks, highlighting the potential it has to considerably improve data efficiency. We further consider the many new biologically inspired approaches that have emerged in recent years, focusing on those that utilize regularization, modularity, memory, and meta-learning, and highlight some of the most promising and impactful directions.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Current approaches suffer from significant limitations including the lack of rigorous theoretical frameworks for characterizing forgetting bounds and the absence of principled optimization strategies that can effectively balance plasticity-stability trade-offs.
“Despite these promising directions, current approaches suffer from significant limitations including the lack of rigorous theoretical frameworks for characterizing forgetting bounds and the absence of principled optimization strategies that can effectively balance plasticity-stability trade-offs6.”
Cites
Overcoming catastrophic forgetting in neural networks
Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A. A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al. (2017) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1611835114 · Cited by 7,899 · see citing works
Self-citationTowards Deep Learning Models Resistant to Adversarial Attacks
Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2017) · arXiv · doi:10.48550/arxiv.1706.06083 · Cited by 6,602 · see citing works
Bengio, Y., Louradour, J., Collobert, R., & Weston, J. (2009) · Proceedings of the 26th Annual International Conference on Machine Learning · doi:10.1145/1553374.1553380 · Cited by 5,366 · cited 1× · see citing works
“Compared with curriculum learning [12,13], the learner does not control the task ordering.”
BackgroundiCaRL: Incremental Classifier and Representation Learning
Rebuffi, S.-A., Kolesnikov, A., Sperl, G., & Lampert, C. H. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.587 · Cited by 3,988 · see citing works
Memory Aware Synapses: Learning What (not) to Forget
Aljundi, R., Babiloni, F., Elhoseiny, M., Rohrbach, M., & Tuytelaars, T. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01219-9_9 · Cited by 1,590 · see citing works
Neuroscience-Inspired Artificial Intelligence
Hassabis, D., Kumaran, D., Summerfield, C., & Botvinick, M. (2017) · Neuron · doi:10.1016/j.neuron.2017.06.011 · Cited by 1,557 · see citing works
Catastrophic forgetting, rehearsal and pseudorehearsal
ROBINS, A. (1995) · Connection Science · doi:10.1080/09540099550039318 · Cited by 833 · see citing works
Learning Sparse Neural Networks through $L_0$ Regularization
Louizos, C., Welling, M., & Kingma, D. P. (2017) · arXiv · doi:10.48550/arxiv.1712.01312 · Cited by 628 · see citing works
Learning to reinforcement learn
Wang, J. X., Kurth-Nelson, Z., Tirumala, D., Soyer, H., Leibo, J. Z., Munos, R., Blundell, C., Kumaran, D., & Botvinick, M. (2016) · arXiv · doi:10.48550/arxiv.1611.05763 · Cited by 579 · see citing works
Human replay spontaneously reorganizes experience
Liu, Y., Dolan, R. J., Kurth-Nelson, Z., & Behrens, T. E. J. (2019) · Cell · doi:10.1016/j.cell.2019.06.012 · Cited by 497 · see citing works
Encoder Based Lifelong Learning
Rannen, A., Aljundi, R., Blaschko, M. B., & Tuytelaars, T. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.148 · Cited by 324 · see citing works
Overcoming catastrophic forgetting with hard attention to the task
Serrà, J., Surís, D., Miron, M., & Karatzoglou, A. (2018) · arXiv · doi:10.48550/arxiv.1801.01423 · Cited by 213 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Wang, L., Zhang, X., Su, H., & Zhu, J. (2024) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3367329 · Cited by 1,113 · see citing works
“In response to external Manuscript received 13 February 2023; revised 13 September 2023; accepted changes, evolution has empowered human and other organisms with strong adaptability to continually acquire, update, accumulate and exploit knowledge [1], [2], [3].”
BackgroundInfluentialThree types of incremental learning
van de Ven, G. M., Tuytelaars, T., & Tolias, A. S. (2022) · Nature Machine Intelligence · doi:10.1038/s42256-022-00568-3 · Cited by 665 · see citing works
Towards Continual Reinforcement Learning: A Review and Perspectives
Khetarpal, K., Riemer, M., Rish, I., & Precup, D. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13673 · Cited by 224 · see citing works
A collective AI via lifelong learning and sharing at the edge
Soltoggio, A., Ben-Iwhiwhu, E., Braverman, V., Eaton, E., Epstein, B., Ge, Y., Halperin, L., How, J., Itti, L., Jacobs, M. A., et al. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00800-2 · Cited by 51 · see citing works
A Definition of Continual Reinforcement Learning
Abel, D., Barreto, A., Roy, B. V., Precup, D., Hasselt, H. V., & Singh, S. (2023) · Advances in Neural Information Processing Systems 36 · doi:10.52202/075280-2192 · Cited by 36 · see citing works
Yao, J., & Kowal, J. (2025) · Energy and AI · doi:10.1016/j.egyai.2025.100585 · Cited by 30 · see citing works
Fan, C., Hahn, N., Kamdar, F., Avansino, D., Wilson, G. H., Hochberg, L., Shenoy, K. V., Henderson, J. M., & Willett, F. R. (2023) · arXiv · doi:10.48550/arxiv.2311.03611 · Cited by 19 · see citing works
General intelligence requires rethinking exploration
Jiang, M., Rocktäschel, T., & Grefenstette, E. (2022) · arXiv · doi:10.48550/arxiv.2211.07819 · Cited by 17
Input-driven dynamics for robust memory retrieval in Hopfield networks
Betteti, S., Baggio, G., Bullo, F., & Zampieri, S. (2025) · Science Advances · doi:10.1126/sciadv.adu6991 · Cited by 12 · see citing works
“…of these limitations, we advocate for a paradigm shift from a two-step mechanism, akin to a standard algorithmic approach, to a input-driven dynamic mechanism, aligned with the principles of online algorithms and continual learning [Zenke et al., 2017, Hadsell et al., 2020, Lesort et al., 2020].”
Loss of Plasticity in Continual Deep Reinforcement Learning
Abbas, Z., Zhao, R., Modayil, J., White, A., & Machado, M. C. (2023) · arXiv · doi:10.48550/arxiv.2303.07507 · Cited by 10 · see citing works
Zhou, S., & Li, Q. (2025) · Scientific Reports · doi:10.1038/s41598-025-31685-9
End-to-End Test-Time Training for Long Context
Tandon, A., Dalal, K., Li, X., Koceja, D., Rød, M., Buchanan, S., Wang, X., Leskovec, J., Koyejo, S., Hashimoto, T., et al. (2025) · arXiv
“Conventionally, continual learning as a research field has focused on learning from a distribution that gradually changes over time [68, 96, 33].”
Mind the Gap: Assessing Temporal Generalization in Neural Language Models
Lazaridou, A., Kuncoro, A., Gribovskaya, E., Agrawal, D., Liska, A., Terzi, T., Gimenez, M., d'Autume, C. D. M., Kocisky, T., Ruder, S., et al. (2021) · arXiv · doi:10.48550/arxiv.2102.01951 · Cited by 90 · see citing works
- Authors
- Hadsell, R., Rao, D., Rusu, A. A., & Pascanu, R.
- Affiliations
- Google DeepMind (United Kingdom) (GB)
- Corresponding author
- Hadsell, Raia
- Venue
- Trends in Cognitive Sciences
- Publisher
- Elsevier BV
- Published
- 2020-12
- Volume
- 24
- Issue
- 12
- Pages
- 1028-1040
- ISSN
- 1364-6613 (ISSN-L)
- OpenAlex
- W3097816393
- Cited by
- 467
- References
- 12
- Citations by year
- 2026: 62 · 2025: 113 · 2024: 104 · 2023: 87 · 2022: 62 · 2021: 39
- FWCI
- 1.63
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Trends in Cognitive Sciences (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Data Stream Mining Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- continual learning, deep neural network, learning dynamics, data efficiency, biologically inspired learning, regularization, modularity, memory, meta-learning, catastrophic forgetting
- MeSH terms
- Artificial Intelligence, Humans, Learning, Memory, Neural Networks, Computer
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
