{"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/differentiable-plasticity-training-plastic","title":"Differentiable plasticity: training plastic neural networks with backpropagation","arxiv_id":"1804.02464","date":"2018-04-06","proceeding":"ICML 2018 7","authors":["Thomas Miconi","Jeff Clune","Kenneth O. Stanley"],"abstract":"How can we build agents that keep learning from experience, quickly and\nefficiently, after their initial training? Here we take inspiration from the\nmain mechanism of learning in biological brains: synaptic plasticity, carefully\ntuned by evolution to produce efficient lifelong learning. We show that\nplasticity, just like connection weights, can be optimized by gradient descent\nin large (millions of parameters) recurrent networks with Hebbian plastic\nconnections. First, recurrent plastic networks with more than two million\nparameters can be trained to memorize and reconstruct sets of novel,\nhigh-dimensional 1000+ pixels natural images not seen during training.\nCrucially, traditional non-plastic recurrent networks fail to solve this task.\nFurthermore, trained plastic networks can also solve generic meta-learning\ntasks such as the Omniglot task, with competitive results and little parameter\noverhead. Finally, in reinforcement learning settings, plastic networks\noutperform a non-plastic equivalent in a maze exploration task. We conclude\nthat differentiable plasticity may provide a powerful novel approach to the\nlearning-to-learn problem.","url_abs":"http://arxiv.org/abs/1804.02464v3","url_pdf":"http://arxiv.org/pdf/1804.02464v3.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":"differentiable-plasticity-training-plastic","repo_url":"https://github.com/uber-common/differentiable-plasticity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"differentiable-plasticity-training-plastic","repo_url":"https://github.com/darylfung96/differentiable_plasticity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"differentiable-plasticity-training-plastic","repo_url":"https://github.com/jurastm/differentiable_neural_plasticity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"differentiable-plasticity-training-plastic","repo_url":"https://github.com/uber-research/backpropamine","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"NOASSERTION"}},{"paper_slug":"differentiable-plasticity-training-plastic","repo_url":"https://github.com/uber-research/differentiable-plasticity","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"lifelong-learning","task_name":"Lifelong learning"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.02464","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.02464"}},"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/uber-research/differentiable-plasticity","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber-research/backpropamine","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/darylfung96/differentiable_plasticity","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/uber-common/differentiable-plasticity","reach":{"status":"ok","spdx":"NOASSERTION"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/jurastm/differentiable_neural_plasticity","reach":{"status":"ok"}}],"summary":{"unverified":1},"by_repo_kind":{"listed":{"samples":1,"ran":0,"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":1,"samples":[{"code_sha256_prefix":"96ff09a68680e5c2","entry":"generateInputsAndTarget","repo":"uber-research/differentiable-plasticity","repo_kind":"listed","path":"images/images.py","file_url":"https://github.com/uber-research/differentiable-plasticity/blob/HEAD/images/images.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"96ff09a68680e5c2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}