{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/learning-to-continually-learn","title":"Learning to Continually Learn","arxiv_id":"2002.09571","date":"2020-02-21","proceeding":null,"authors":["Shawn Beaulieu","Lapo Frati","Thomas Miconi","Joel Lehman","Kenneth O. Stanley","Jeff Clune","Nick Cheney"],"abstract":"Continual lifelong learning requires an agent or model to learn many sequentially ordered tasks, building on previous knowledge without catastrophically forgetting it. Much work has gone towards preventing the default tendency of machine learning models to catastrophically forget, yet virtually all such work involves manually-designed solutions to the problem. We instead advocate meta-learning a solution to catastrophic forgetting, allowing AI to learn to continually learn. Inspired by neuromodulatory processes in the brain, we propose A Neuromodulated Meta-Learning Algorithm (ANML). It differentiates through a sequential learning process to meta-learn an activation-gating function that enables context-dependent selective activation within a deep neural network. Specifically, a neuromodulatory (NM) neural network gates the forward pass of another (otherwise normal) neural network called the prediction learning network (PLN). The NM network also thus indirectly controls selective plasticity (i.e. the backward pass of) the PLN. ANML enables continual learning without catastrophic forgetting at scale: it produces state-of-the-art continual learning performance, sequentially learning as many as 600 classes (over 9,000 SGD updates).","url_abs":"https://arxiv.org/abs/2002.09571v2","url_pdf":"https://arxiv.org/pdf/2002.09571v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"learning-to-continually-learn","repo_url":"https://github.com/uvm-neurobotics-lab/ANML","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-continually-learn","repo_url":"https://github.com/blues-lin/fin-analyze","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-to-continually-learn","repo_url":"https://github.com/maPiche/ANML-Project","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-continually-learn","repo_url":"https://github.com/sebamenabar/oaml-jax","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"learning-to-continually-learn","repo_url":"https://github.com/shawnbeaulieu/ANML","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"continual-learning","task_name":"Continual Learning"},{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"}],"methods":[{"method_slug":"sgd","method_name":"SGD"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2002.09571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2002.09571"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/blues-lin/fin-analyze","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uvm-neurobotics-lab/ANML","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/sebamenabar/oaml-jax","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/maPiche/ANML-Project","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shawnbeaulieu/ANML","reach":{"status":"ok"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":2},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"ea5fa769b4fc0bf3","entry":"flatten","repo":"sebamenabar/oaml-jax","repo_kind":"listed","path":"src/lib.py","file_url":"https://github.com/sebamenabar/oaml-jax/blob/HEAD/src/lib.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ea5fa769b4fc0bf3"}},{"code_sha256_prefix":"7e4ead0ed36ad6cc","entry":"xe_and_acc","repo":"sebamenabar/oaml-jax","repo_kind":"listed","path":"src/lib.py","file_url":"https://github.com/sebamenabar/oaml-jax/blob/HEAD/src/lib.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7e4ead0ed36ad6cc"}},{"code_sha256_prefix":"9db3d82f1ac7d4cd","entry":"xe_loss","repo":"sebamenabar/oaml-jax","repo_kind":"listed","path":"src/lib.py","file_url":"https://github.com/sebamenabar/oaml-jax/blob/HEAD/src/lib.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9db3d82f1ac7d4cd"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}