{"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/efficient-activation-function-optimization","title":"Efficient Activation Function Optimization through Surrogate Modeling","arxiv_id":"2301.05785","date":"2023-01-13","proceeding":"NeurIPS 2023 11","authors":["Garrett Bingham","Risto Miikkulainen"],"abstract":"Carefully designed activation functions can improve the performance of neural networks in many machine learning tasks. However, it is difficult for humans to construct optimal activation functions, and current activation function search algorithms are prohibitively expensive. This paper aims to improve the state of the art through three steps: First, the benchmark datasets Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT were created by training convolutional, residual, and vision transformer architectures from scratch with 2,913 systematically generated activation functions. Second, a characterization of the benchmark space was developed, leading to a new surrogate-based method for optimization. More specifically, the spectrum of the Fisher information matrix associated with the model's predictive distribution at initialization and the activation function's output distribution were found to be highly predictive of performance. Third, the surrogate was used to discover improved activation functions in several real-world tasks, with a surprising finding: a sigmoidal design that outperformed all other activation functions was discovered, challenging the status quo of always using rectifier nonlinearities in deep learning. Each of these steps is a contribution in its own right; together they serve as a practical and theoretical foundation for further research on activation function optimization.","url_abs":"https://arxiv.org/abs/2301.05785v6","url_pdf":"https://arxiv.org/pdf/2301.05785v6.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":"efficient-activation-function-optimization","repo_url":"https://github.com/cognizant-ai-labs/aquasurf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"efficient-activation-function-optimization","repo_url":"https://github.com/cognizant-ai-labs/act-bench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[],"methods":[{"method_slug":"attention","method_name":"Attention"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"vision-transformer","method_name":"Vision Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2301.05785","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2301.05785"}},"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/cognizant-ai-labs/aquasurf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/cognizant-ai-labs/act-bench","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":1,"ran_honours":2},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":3,"samples":[{"code_sha256_prefix":"e35de05dedac9df3","entry":"ActivationFunction","repo":"cognizant-ai-labs/aquasurf","repo_kind":"official","path":"aquasurf/activation.py","file_url":"https://github.com/cognizant-ai-labs/aquasurf/blob/HEAD/aquasurf/activation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"e35de05dedac9df3"}},{"code_sha256_prefix":"262e59bec97f68e0","entry":"gaussian_mean","repo":"cognizant-ai-labs/aquasurf","repo_kind":"official","path":"aquasurf/activation.py","file_url":"https://github.com/cognizant-ai-labs/aquasurf/blob/HEAD/aquasurf/activation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"262e59bec97f68e0"}},{"code_sha256_prefix":"233c27715946e197","entry":"second_moment","repo":"cognizant-ai-labs/aquasurf","repo_kind":"official","path":"aquasurf/activation.py","file_url":"https://github.com/cognizant-ai-labs/aquasurf/blob/HEAD/aquasurf/activation.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"233c27715946e197"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}