Biologically Inspired Sleep Algorithm for Reducing Catastrophic Forgetting in Neural Networks
Open accessAbstract
Artificial neural networks (ANNs) are known to suffer from catastrophic forgetting: when learning multiple tasks, they perform well on the most recently learned task while failing to perform on previously learned tasks. In biological networks, sleep is known to play a role in memory consolidation and incremental learning. Motivated by the processes that are known to be involved in sleep generation in biological networks, we developed an algorithm that implements a sleep-like phase in ANNs. In an incremental learning framework, we demonstrate that sleep is able to recover older tasks that were otherwise forgotten. We show that sleep creates unique representations of each class of inputs and neurons that were relevant to previous tasks fire during sleep, simulating replay of previously learned memories.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 AI systems employ binary retention strategies that either preserve everything within their capacity or lose it entirely.
“current AI systems employ binary retention strategies that either preserve everything within their capacity or lose it entirely [16, 17].”
From FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory (2026) · cites this paper as [16]
The Abstract (p. 1) says ANNs can perform well on a recently learned task while failing on earlier tasks, supporting the claim’s concern about forgetting. But the Sleep Algorithm (p. 1) says information from older tasks may remain even when classification performance suggests it was forgotten. The paper does not describe a binary strategy of preserving everything or losing it entirely. (LLM, conf=0.85)
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Rasch, B., & Born, J. (2013) · Physiological Reviews · doi:10.1152/physrev.00032.2012 · Cited by 2,783 · cited 1× · see citing works
“In biological networks, sleep has been hypothesized to play an important role in memory consolidation and generalization of knowledge (Rasch and Born 2013).”
Background
Flagged first, then by citations
Research works printed but not linked: 4
- Diehl, P. U.; Neil, D.; Binas, J.; Cook, M.; Liu, S.-C.; and Pfeiffer, M. 2015. Fast-classifying, high-accuracy spiking deep networks through weight and threshold balancing. In 2015 International Joint Conference on Neural Networks (IJCNN) , 1-8. IEEE.
- Gonzalez, O. C.; Sokolov, Y.; Krishnan, G.; and Bazhenov, M. 2019. Can sleep protect memories from catastrophic forgetting? BioRxiv 569038.
- Ji, D., and Wilson, M. A. 2007. Coordinated memory replay in the visual cortex and hippocampus during sleep. Nature neuroscience 10(1):100.
- McClelland, J. L.; McNaughton, B. L.; and O'reilly, R. C. 1995. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychological review 102(3):419.
Cited by
Sorted by citations
Replay in Deep Learning: Current Approaches and Missing Biological Elements
Hayes, T. L., Krishnan, G. P., Bazhenov, M., Siegelmann, H. T., Sejnowski, T. J., & Kanan, C. (2021) · Neural Computation · doi:10.1162/neco_a_01433 · Cited by 106 · see citing works
Self-citationFadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
Wei, L., Dong, X., Peng, X., Xie, N., & Wang, B. (2026) · ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp55912.2026.11462095 · Cited by 1 · see citing works
FadeMem: Biologically-Inspired Forgetting for Efficient Agent Memory
Wei, L., Peng, X., Dong, X., Xie, N., & Wang, B. (2026) · arXiv
“…balances retention and forgetting through natural decay processes, where unim-portant information gradually fades while significant memories are reinforced, current AI systems employ binary retention strategies that either preserve everything within their capacity or lose it entirely [16, 17].”
- Authors
- Tadros, T., Krishnan, G., Ramyaa, R., & Bazhenov, M.
- Affiliations
- University of California San Diego (US)
- New Mexico Institute of Mining and Technology (US)
- Venue
- Proceedings of the AAAI Conference on Artificial Intelligence
- Published
- 2020-04-03
- Volume
- 34
- Issue
- 10
- Pages
- 13933-13934
- ISSN
- 2159-5399 (ISSN-L)
- 2374-3468
- OpenAlex
- W3037715783
- Cited by
- 9
- References
- 1
- Citations by year
- 2026: 1 · 2025: 1 · 2023: 2 · 2022: 2 · 2021: 2 · 2019: 1
- FWCI
- 0.57
- Type
- conference paper
- Language
- en
- Open access
- diamond
- doi.org
- Licence
- www.aaai.org/ (unspecified)
- Locations
- Proceedings of the AAAI Conference on Artificial Intelligence (publishedVersion)
- AAAI Publications (The Association for the Advancement of Artificial Intelligence (AAAI)) (submittedVersion)
- Funders
- Defense Advanced Research Projects Agency (# HR0011-18-2-0021, HR0011)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Life Sciences › Neuroscience › Cognitive Neuroscience › Memory and Neural Mechanisms
- Keywords
- catastrophic forgetting, memory consolidation, incremental learning, memory replay, bio-inspired algorithms, neural network training
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
