{"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/credit-assignment-in-neural-networks-through","title":"Credit Assignment in Neural Networks through Deep Feedback Control","arxiv_id":"2106.07887","date":"2021-06-15","proceeding":"NeurIPS 2021 12","authors":["Alexander Meulemans","Matilde Tristany Farinha","Javier García Ordóñez","Pau Vilimelis Aceituno","João Sacramento","Benjamin F. Grewe"],"abstract":"The success of deep learning sparked interest in whether the brain learns by using similar techniques for assigning credit to each synaptic weight for its contribution to the network output. However, the majority of current attempts at biologically-plausible learning methods are either non-local in time, require highly specific connectivity motives, or have no clear link to any known mathematical optimization method. Here, we introduce Deep Feedback Control (DFC), a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. The resulting learning rule is fully local in space and time and approximates Gauss-Newton optimization for a wide range of feedback connectivity patterns. To further underline its biological plausibility, we relate DFC to a multi-compartment model of cortical pyramidal neurons with a local voltage-dependent synaptic plasticity rule, consistent with recent theories of dendritic processing. By combining dynamical system theory with mathematical optimization theory, we provide a strong theoretical foundation for DFC that we corroborate with detailed results on toy experiments and standard computer-vision benchmarks.","url_abs":"https://arxiv.org/abs/2106.07887v3","url_pdf":"https://arxiv.org/pdf/2106.07887v3.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":"credit-assignment-in-neural-networks-through","repo_url":"https://github.com/meulemansalex/deep_feedback_control","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"credit-assignment-in-neural-networks-through","repo_url":"https://github.com/mariacer/strong_dfc","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"credit-assignment-in-neural-networks-through","repo_url":"https://github.com/pennfranc/bio-inspired-continual-learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.07887","atlas_url":"https://app.syntology.ai/?focus=2106.07887","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.07887"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/mariacer/strong_dfc","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/meulemansalex/deep_feedback_control","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pennfranc/bio-inspired-continual-learning","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":4},"by_repo_kind":{"official":{"samples":4,"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":0,"samples":[{"code_sha256_prefix":"6cbab1fbc806547f","entry":"add_avg_angles","repo":"meulemansalex/deep_feedback_control","repo_kind":"official","path":"run_pipeline.py","file_url":"https://github.com/meulemansalex/deep_feedback_control/blob/HEAD/run_pipeline.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cbab1fbc806547f"}},{"code_sha256_prefix":"455a9fc07be21f8a","entry":"all_negative_eig","repo":"meulemansalex/deep_feedback_control","repo_kind":"official","path":"run_toy_exp_fig2.py","file_url":"https://github.com/meulemansalex/deep_feedback_control/blob/HEAD/run_toy_exp_fig2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"455a9fc07be21f8a"}},{"code_sha256_prefix":"6cf7b989a477474f","entry":"all_positive_eig","repo":"meulemansalex/deep_feedback_control","repo_kind":"official","path":"run_toy_exp_fig2.py","file_url":"https://github.com/meulemansalex/deep_feedback_control/blob/HEAD/run_toy_exp_fig2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6cf7b989a477474f"}},{"code_sha256_prefix":"6f6796599c1e16d3","entry":"rescale","repo":"meulemansalex/deep_feedback_control","repo_kind":"official","path":"run_toy_exp_fig2.py","file_url":"https://github.com/meulemansalex/deep_feedback_control/blob/HEAD/run_toy_exp_fig2.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f6796599c1e16d3"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}