{"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/bidirectional-self-normalizing-neural","title":"Bidirectionally Self-Normalizing Neural Networks","arxiv_id":"2006.12169","date":"2020-06-22","proceeding":null,"authors":["Yao Lu","Stephen Gould","Thalaiyasingam Ajanthan"],"abstract":"The problem of vanishing and exploding gradients has been a long-standing obstacle that hinders the effective training of neural networks. Despite various tricks and techniques that have been employed to alleviate the problem in practice, there still lacks satisfactory theories or provable solutions. In this paper, we address the problem from the perspective of high-dimensional probability theory. We provide a rigorous result that shows, under mild conditions, how the vanishing/exploding gradients problem disappears with high probability if the neural networks have sufficient width. Our main idea is to constrain both forward and backward signal propagation in a nonlinear neural network through a new class of activation functions, namely Gaussian-Poincar\\'e normalized functions, and orthogonal weight matrices. Experiments on both synthetic and real-world data validate our theory and confirm its effectiveness on very deep neural networks when applied in practice.","url_abs":"https://arxiv.org/abs/2006.12169v5","url_pdf":"https://arxiv.org/pdf/2006.12169v5.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":"bidirectional-self-normalizing-neural","repo_url":"https://github.com/madsen-s-research-group/neuralil-public-releases","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.12169","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.12169"}},"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/madsen-s-research-group/neuralil-public-releases","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":12},"by_repo_kind":{"listed":{"samples":12,"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":"d749f18fa895dd8e","entry":"build_Legendre_polynomials","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/bessel_descriptors.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/bessel_descriptors.py","link_basis":"harvester_set","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":"d749f18fa895dd8e"}},{"code_sha256_prefix":"68a0f0bb9847d79c","entry":"calc_morse_mixing_radii","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/model.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/model.py","link_basis":"harvester_set","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":"68a0f0bb9847d79c"}},{"code_sha256_prefix":"1bad6aeb7bf9ed02","entry":"center_at_point","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/bessel_descriptors.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/bessel_descriptors.py","link_basis":"harvester_set","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":"1bad6aeb7bf9ed02"}},{"code_sha256_prefix":"d9a88c22771f5b74","entry":"center_at_points","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/bessel_descriptors.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/bessel_descriptors.py","link_basis":"harvester_set","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":"d9a88c22771f5b74"}},{"code_sha256_prefix":"13da0d69970b315f","entry":"create_array_shuffler","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/utilities.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/utilities.py","link_basis":"harvester_set","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":"13da0d69970b315f"}},{"code_sha256_prefix":"12e4625946654978","entry":"create_gp_activation","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/utilities.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/utilities.py","link_basis":"harvester_set","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":"12e4625946654978"}},{"code_sha256_prefix":"4b64c4de90b0fd21","entry":"create_j_l","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/spherical_bessel/functions.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/spherical_bessel/functions.py","link_basis":"harvester_set","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":"4b64c4de90b0fd21"}},{"code_sha256_prefix":"245374857fea32b5","entry":"create_log_cosh","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/training.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/training.py","link_basis":"harvester_set","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":"245374857fea32b5"}},{"code_sha256_prefix":"78f1b6a73695de86","entry":"create_one_cycle_minimizer","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/training.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/training.py","link_basis":"harvester_set","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":"78f1b6a73695de86"}},{"code_sha256_prefix":"b149d49a06fdfe4f","entry":"reset_one_cycle_minimizer","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/training.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/training.py","link_basis":"harvester_set","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":"b149d49a06fdfe4f"}},{"code_sha256_prefix":"570e0e0792cf8d8a","entry":"smooth_cutoff","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/model.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/model.py","link_basis":"harvester_set","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":"570e0e0792cf8d8a"}},{"code_sha256_prefix":"1fa3157096c56198","entry":"update_energy_offset","repo":"madsen-s-research-group/neuralil-public-releases","repo_kind":"listed","path":"src/neuralil/utilities.py","file_url":"https://github.com/madsen-s-research-group/neuralil-public-releases/blob/HEAD/src/neuralil/utilities.py","link_basis":"harvester_set","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":"1fa3157096c56198"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}