{"id":"doi:10.1073/pnas.1611835114","title":"Overcoming catastrophic forgetting in neural networks","date":"2017-03-14","section":"Data, training, optimization","quality":0.012852,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/","source_url":"https://doi.org/10.1073/pnas.1611835114","text_available":true,"authors":["James Kirkpatrick","Razvan Pascanu","Neil Rabinowitz","Joel Veness"],"outgoing":[{"source":"doi:10.1073/pnas.1611835114","target":"arxiv:1509.06461","evidence":"title","id":"arxiv:1509.06461","title":"Deep Reinforcement Learning with Double Q-learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/a2f115ac879cd2efb9548baf3ecdcb925d2492f03b4b0940720f6e5b0840715b/"}],"incoming":[{"source":"arxiv:1708.02072","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:1708.02072","title":"Measuring Catastrophic Forgetting in Neural Networks","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/358d4d451093ba5234c459f6323da4968d71d8be905b6612f5bae0162e9145f2/"},{"source":"arxiv:1905.10985","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:1905.10985","title":"AI-GAs: AI-generating algorithms, an alternate paradigm for producing general artificial intelligence","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/089142f7297bed414d01b82c78dc888e4018fecff7efbe5cae66442e03f87c4b/"},{"source":"arxiv:2108.06325","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2108.06325","title":"Continual Backprop: Stochastic Gradient Descent with Persistent Randomness","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/73c90c52bffd8b5b2485d93607350545d822f361c29d3c0063b8d3025576e793/"},{"source":"arxiv:2312.00276","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2312.00276","title":"Metalearning Continual Learning Algorithms","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d7361f404c0455d9f759fc6a8dd7bd1da75146e72717b7a2fbcdb8bac80412a/"},{"source":"arxiv:2402.13669","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2402.13669","title":"Self-Distillation Bridges Distribution Gap in Language Model Fine-Tuning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1a8d11d48a58f35055e7f88f699cf42688a3698c63bd7026d5789f72a80581bf/"},{"source":"arxiv:2403.05175","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2403.05175","title":"Continual Learning and Catastrophic Forgetting","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/3ed9ae586e8898d0235553d62c5f002609d3d112cbec54cc46655d19ff736400/"},{"source":"arxiv:2404.09173","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2404.09173","title":"TransformerFAM: Feedback attention is working memory","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cbd04248dee4a37ffe8957d53e0b260196e25a477e8aa86db09efcd9fee74326/"},{"source":"arxiv:2503.21676","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2503.21676","title":"How do language models learn facts? Dynamics, curricula and hallucinations","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/2ef59e7bcfcfc0e4bab638835504ad8a0d2f50665a9797edc09e8628e9b3c0b6/"},{"source":"arxiv:2512.24695","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2512.24695","title":"Nested Learning: The Illusion of Deep Learning Architectures","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/d19bf2367894704a701d0741e7db6d8b148719af1d634b55f5797aab5f617d06/"},{"source":"arxiv:2601.03192","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2601.03192","title":"MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4f5bbf3318b1fe409e0ef5dad02157180b844de366d194e82ce74bc997912eff/"},{"source":"arxiv:2601.16175","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2601.16175","title":"Learning to Discover at Test Time","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/5d0b45cbbc72945765e689cbfb7ac7e4e92dfbb764861b27682ac0744ef05b70/"},{"source":"arxiv:2601.19897","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2601.19897","title":"Self-Distillation Enables Continual Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/cc146df3e9ca40c6d111a5264e08710100c1b34bd0eabd9052e8d55d13589efe/"},{"source":"arxiv:2601.20861","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2601.20861","title":"Evolutionary Strategies lead to Catastrophic Forgetting in LLMs","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/4178758b0cb3ebc95f6a3cbc6423e8ea05c0ae649e11a2f4059a84b3faa6cde0/"},{"source":"arxiv:2607.13104","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2607.13104","title":"Self-Improvements in Modern Agentic Systems: A Survey","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/1452caf7b16ffdb8c2efd5093f46dc4df0f89c3d45a5566cd5fdafd69385b2a7/"},{"source":"arxiv:2610.02140","target":"doi:10.1073/pnas.1611835114","evidence":"title","id":"arxiv:2610.02140","title":"Finetuning with Sampling: SFT Learns Better Than You Think","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/60f5edfae92f505bf86e8890135a44b4129825b0525b5ad8d242e8ba04182605/"},{"source":"doi:10.1038/s41586-024-07711-7","target":"doi:10.1073/pnas.1611835114","evidence":"id","id":"doi:10.1038/s41586-024-07711-7","title":"Maintaining Plasticity in Deep Continual Learning","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/b5d46327415fe38f2b9160b874735530939961a71536f7f1ac4c0dc7a3af3224/"},{"source":"doi:10.1371/journal.pcbi.1010628","target":"doi:10.1073/pnas.1611835114","evidence":"id","id":"doi:10.1371/journal.pcbi.1010628","title":"Sleep prevents catastrophic forgetting in spiking neural networks by forming joint synaptic weight representations","url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/7e34ad47e15cfd27cb9f93eef1399cfa51820e1382157b2c698c13548efc960a/"}],"text_parts":[{"start":0,"end":12480,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/part-1.html"},{"start":12480,"end":25992,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/part-2.html"},{"start":25992,"end":40986,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/part-3.html"},{"start":40986,"end":49810,"url":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/part-4.html"}],"contents":[],"text_code_points":49810,"source_markdown":"https://vinnik-dmitry07.github.io/favorite-papers/agents/papers/849082368a44d06b93ef3ba95bcfddc6672b7a5e8064ad2b2d19601639266e8b/source.md"}