{"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/large-scale-evolution-of-image-classifiers","title":"Large-Scale Evolution of Image Classifiers","arxiv_id":"1703.01041","date":"2017-03-03","proceeding":"ICML 2017 8","authors":["Esteban Real","Sherry Moore","Andrew Selle","Saurabh Saxena","Yutaka Leon Suematsu","Jie Tan","Quoc Le","Alex Kurakin"],"abstract":"Neural networks have proven effective at solving difficult problems but\ndesigning their architectures can be challenging, even for image classification\nproblems alone. Our goal is to minimize human participation, so we employ\nevolutionary algorithms to discover such networks automatically. Despite\nsignificant computational requirements, we show that it is now possible to\nevolve models with accuracies within the range of those published in the last\nyear. Specifically, we employ simple evolutionary techniques at unprecedented\nscales to discover models for the CIFAR-10 and CIFAR-100 datasets, starting\nfrom trivial initial conditions and reaching accuracies of 94.6% (95.6% for\nensemble) and 77.0%, respectively. To do this, we use novel and intuitive\nmutation operators that navigate large search spaces; we stress that no human\nparticipation is required once evolution starts and that the output is a\nfully-trained model. Throughout this work, we place special emphasis on the\nrepeatability of results, the variability in the outcomes and the computational\nrequirements.","url_abs":"http://arxiv.org/abs/1703.01041v2","url_pdf":"http://arxiv.org/pdf/1703.01041v2.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":"large-scale-evolution-of-image-classifiers","repo_url":"https://github.com/StevenGerrad/large-scale-Evolution-Net","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"large-scale-evolution-of-image-classifiers","repo_url":"https://github.com/marijnvk/LargeScaleEvolution","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"evolutionary-algorithms","task_name":"Evolutionary Algorithms"},{"task_slug":"hyperparameter-optimization","task_name":"Hyperparameter Optimization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"architecture-search","task_name":"Neural Architecture Search"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Evolution ensemble","rank_in_archive_order":129,"of":265,"metrics":{"Percentage correct":"95.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Evolution","rank_in_archive_order":153,"of":265,"metrics":{"Percentage correct":"94.6"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Evolution","rank_in_archive_order":144,"of":211,"metrics":{"Percentage correct":"77"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1703.01041","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1703.01041"}},"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/StevenGerrad/large-scale-Evolution-Net","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marijnvk/LargeScaleEvolution","reach":null}],"summary":{"ran_violates":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":"3d0130c3cdb7fe0e","entry":"arg_bool_to_bool","repo":"marijnvk/LargeScaleEvolution","repo_kind":"listed","path":"lse/lse_main.py","file_url":"https://github.com/marijnvk/LargeScaleEvolution/blob/HEAD/lse/lse_main.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"3d0130c3cdb7fe0e"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}