{"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/benchmarking-the-accuracy-and-robustness-of","title":"Benchmarking the Accuracy and Robustness of Feedback Alignment Algorithms","arxiv_id":"2108.13446","date":"2021-08-30","proceeding":null,"authors":["Albert Jiménez Sanfiz","Mohamed Akrout"],"abstract":"Backpropagation is the default algorithm for training deep neural networks due to its simplicity, efficiency and high convergence rate. However, its requirements make it impossible to be implemented in a human brain. In recent years, more biologically plausible learning methods have been proposed. Some of these methods can match backpropagation accuracy, and simultaneously provide other extra benefits such as faster training on specialized hardware (e.g., ASICs) or higher robustness against adversarial attacks. While the interest in the field is growing, there is a necessity for open-source libraries and toolkits to foster research and benchmark algorithms. In this paper, we present BioTorch, a software framework to create, train, and benchmark biologically motivated neural networks. In addition, we investigate the performance of several feedback alignment methods proposed in the literature, thereby unveiling the importance of the forward and backward weight initialization and optimizer choice. Finally, we provide a novel robustness study of these methods against state-of-the-art white and black-box adversarial attacks.","url_abs":"https://arxiv.org/abs/2108.13446v1","url_pdf":"https://arxiv.org/pdf/2108.13446v1.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":"benchmarking-the-accuracy-and-robustness-of","repo_url":"https://github.com/jsalbert/biotorch","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"benchmarking","task_name":"Benchmarking"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2108.13446","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.13446"}},"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/jsalbert/biotorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"e3ed2967409446c3","entry":"compute_matrix_angle","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/layers/metrics.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/layers/metrics.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":"e3ed2967409446c3"}},{"code_sha256_prefix":"3bc4327f07eb8b2a","entry":"create_lr_scheduler","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/benchmark/lr_schedulers.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/benchmark/lr_schedulers.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":"3bc4327f07eb8b2a"}},{"code_sha256_prefix":"a32b11110df11fb0","entry":"create_optimizer","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/benchmark/optimizers.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/benchmark/optimizers.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":"a32b11110df11fb0"}},{"code_sha256_prefix":"2d4eddb7d130da49","entry":"le_net_cifar","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/models/le_net.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/models/le_net.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":"2d4eddb7d130da49"}},{"code_sha256_prefix":"181b334188bd08bd","entry":"le_net_mnist","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/models/le_net.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/models/le_net.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":"181b334188bd08bd"}},{"code_sha256_prefix":"d475032f6599d6a2","entry":"resnet20","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/models/small_resnet.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/models/small_resnet.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":"d475032f6599d6a2"}},{"code_sha256_prefix":"39a8f2409ed521f4","entry":"resnet32","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/models/small_resnet.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/models/small_resnet.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":"39a8f2409ed521f4"}},{"code_sha256_prefix":"f136cbda7347a42f","entry":"resnet44","repo":"jsalbert/biotorch","repo_kind":"official","path":"biotorch/models/small_resnet.py","file_url":"https://github.com/jsalbert/biotorch/blob/HEAD/biotorch/models/small_resnet.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":"f136cbda7347a42f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}