{"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/predify-augmenting-deep-neural-networks-with","title":"Predify: Augmenting deep neural networks with brain-inspired predictive coding dynamics","arxiv_id":"2106.02749","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Bhavin Choksi","Milad Mozafari","Callum Biggs O'May","Benjamin Ador","Andrea Alamia","Rufin VanRullen"],"abstract":"Deep neural networks excel at image classification, but their performance is far less robust to input perturbations than human perception. In this work we explore whether this shortcoming may be partly addressed by incorporating brain-inspired recurrent dynamics in deep convolutional networks. We take inspiration from a popular framework in neuroscience: 'predictive coding'. At each layer of the hierarchical model, generative feedback 'predicts' (i.e., reconstructs) the pattern of activity in the previous layer. The reconstruction errors are used to iteratively update the network's representations across timesteps, and to optimize the network's feedback weights over the natural image dataset-a form of unsupervised training. We show that implementing this strategy into two popular networks, VGG16 and EfficientNetB0, improves their robustness against various corruptions and adversarial attacks. We hypothesize that other feedforward networks could similarly benefit from the proposed framework. To promote research in this direction, we provide an open-sourced PyTorch-based package called Predify, which can be used to implement and investigate the impacts of the predictive coding dynamics in any convolutional neural network.","url_abs":"https://arxiv.org/abs/2106.02749v2","url_pdf":"https://arxiv.org/pdf/2106.02749v2.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":"predify-augmenting-deep-neural-networks-with","repo_url":"https://github.com/bhavinc/predify2021","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"predify-augmenting-deep-neural-networks-with","repo_url":"https://github.com/miladmozafari/predify","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.02749","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02749"}},"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/bhavinc/predify2021","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/miladmozafari/predify","reach":null}],"summary":{"ran":2,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"repositories":2}},"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":"6c64172583d94a30","entry":"PCoder","repo":"miladmozafari/predify","repo_kind":"official","path":"predify/modules/base.py","file_url":"https://github.com/miladmozafari/predify/blob/HEAD/predify/modules/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"6c64172583d94a30"}},{"code_sha256_prefix":"66572ffdc4e887c1","entry":"Predictor","repo":"miladmozafari/predify","repo_kind":"official","path":"predify/modules/base.py","file_url":"https://github.com/miladmozafari/predify/blob/HEAD/predify/modules/base.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"GPL-3.0","inline_ok":false,"mcp_get_code":{"code_sha256":"66572ffdc4e887c1"}},{"code_sha256_prefix":"1447c3a6718dcde1","entry":"convert_to_successes","repo":"bhavinc/predify2021","repo_kind":"official","path":"predify2021/adversarial_attacks/analyse_adversarial_attacks.py","file_url":"https://github.com/bhavinc/predify2021/blob/HEAD/predify2021/adversarial_attacks/analyse_adversarial_attacks.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"CC-BY-4.0","inline_ok":false,"mcp_get_code":{"code_sha256":"1447c3a6718dcde1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}