{"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/neural-anisotropy-directions","title":"Neural Anisotropy Directions","arxiv_id":"2006.09717","date":"2020-06-17","proceeding":"NeurIPS 2020 12","authors":["Guillermo Ortiz-Jimenez","Apostolos Modas","Seyed-Mohsen Moosavi-Dezfooli","Pascal Frossard"],"abstract":"In this work, we analyze the role of the network architecture in shaping the inductive bias of deep classifiers. To that end, we start by focusing on a very simple problem, i.e., classifying a class of linearly separable distributions, and show that, depending on the direction of the discriminative feature of the distribution, many state-of-the-art deep convolutional neural networks (CNNs) have a surprisingly hard time solving this simple task. We then define as neural anisotropy directions (NADs) the vectors that encapsulate the directional inductive bias of an architecture. These vectors, which are specific for each architecture and hence act as a signature, encode the preference of a network to separate the input data based on some particular features. We provide an efficient method to identify NADs for several CNN architectures and thus reveal their directional inductive biases. Furthermore, we show that, for the CIFAR-10 dataset, NADs characterize the features used by CNNs to discriminate between different classes.","url_abs":"https://arxiv.org/abs/2006.09717v2","url_pdf":"https://arxiv.org/pdf/2006.09717v2.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":"neural-anisotropy-directions","repo_url":"https://github.com/LTS4/neural-anisotropy-directions","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"neural-anisotropy-directions","repo_url":"https://github.com/VahidZee/nads","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-bias","task_name":"Inductive Bias"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.09717","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.09717"}},"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":"deterministic:regex_extraction","url":"https://github.com/LTS4/neural-anisotropy-directions","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/VahidZee/nads","reach":null}],"summary":{"ran":2,"ran_fixture":2,"unverified":5},"by_repo_kind":{"official":{"samples":2,"ran":2,"repositories":1},"listed":{"samples":7,"ran":2,"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":"39c01bcce404741c","entry":"GradientCovarianceAnisotropyFinder","repo":"LTS4/neural-anisotropy-directions","repo_kind":"official","path":"nad_computation.py","file_url":"https://github.com/LTS4/neural-anisotropy-directions/blob/HEAD/nad_computation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"39c01bcce404741c"}},{"code_sha256_prefix":"0f838c9168e36b16","entry":"NADs","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0f838c9168e36b16"}},{"code_sha256_prefix":"1a7c50021e79245d","entry":"input_numerical_jacobian","repo":"LTS4/neural-anisotropy-directions","repo_kind":"official","path":"nad_computation.py","file_url":"https://github.com/LTS4/neural-anisotropy-directions/blob/HEAD/nad_computation.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1a7c50021e79245d"}},{"code_sha256_prefix":"dc61272119b0560e","entry":"numerical_jacobian","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dc61272119b0560e"}},{"code_sha256_prefix":"ede6d5b4a5394294","entry":"GradientCovariance","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ede6d5b4a5394294"}},{"code_sha256_prefix":"f36de828f2999ceb","entry":"make_subdirectories","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f36de828f2999ceb"}},{"code_sha256_prefix":"9118a1c9f6fc8c15","entry":"visualize_image","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9118a1c9f6fc8c15"}},{"code_sha256_prefix":"9ca12e126bfb8d93","entry":"visualize_nads","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9ca12e126bfb8d93"}},{"code_sha256_prefix":"a840a0cfb6a71e5e","entry":"visualize_spectrum","repo":"VahidZee/nads","repo_kind":"listed","path":"nads/compute/gradient_covariance.py","file_url":"https://github.com/VahidZee/nads/blob/HEAD/nads/compute/gradient_covariance.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a840a0cfb6a71e5e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}