{"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/maxout-networks","title":"Maxout Networks","arxiv_id":"1302.4389","date":"2013-02-18","proceeding":null,"authors":["Ian J. Goodfellow","David Warde-Farley","Mehdi Mirza","Aaron Courville","Yoshua Bengio"],"abstract":"We consider the problem of designing models to leverage a recently introduced\napproximate model averaging technique called dropout. We define a simple new\nmodel called maxout (so named because its output is the max of a set of inputs,\nand because it is a natural companion to dropout) designed to both facilitate\noptimization by dropout and improve the accuracy of dropout's fast approximate\nmodel averaging technique. We empirically verify that the model successfully\naccomplishes both of these tasks. We use maxout and dropout to demonstrate\nstate of the art classification performance on four benchmark datasets: MNIST,\nCIFAR-10, CIFAR-100, and SVHN.","url_abs":"http://arxiv.org/abs/1302.4389v4","url_pdf":"http://arxiv.org/pdf/1302.4389v4.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":"maxout-networks","repo_url":"https://github.com/mavenlin/cuda-convnet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/minoring/nin-tf2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/paniabhisek/maxout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/philipperemy/tensorflow-maxout","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/pmallari/Emotion_Recognition","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/pmallari/Emotion_Recognition_PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"maxout-networks","repo_url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Maxout_Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"maxout","method_name":"Maxout"}],"datasets_introduced":[],"methods_introduced":[{"slug":"maxout","name":"Maxout","full_name":"Maxout"}],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"Maxout Network (k=2)","rank_in_archive_order":200,"of":265,"metrics":{"Percentage correct":"90.65"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"Maxout Network (k=2)","rank_in_archive_order":196,"of":211,"metrics":{"Percentage correct":"61.43"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"Maxout Networks","rank_in_archive_order":33,"of":81,"metrics":{"Percentage error":"0.5"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"Maxout","rank_in_archive_order":36,"of":62,"metrics":{"Percentage error":"2.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1302.4389","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1302.4389"}},"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/mavenlin/cuda-convnet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/paniabhisek/maxout","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/minoring/nin-tf2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pmallari/Emotion_Recognition_PyTorch","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/pmallari/Emotion_Recognition","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/philipperemy/tensorflow-maxout","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/MaximeVandegar/Papers-in-100-Lines-of-Code/tree/main/Maxout_Networks","reach":null}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"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":"9a4cab9e77a16022","entry":"create_bias_variable","repo":"philipperemy/tensorflow-maxout","repo_kind":"listed","path":"mnist_maxout_example.py","file_url":"https://github.com/philipperemy/tensorflow-maxout/blob/HEAD/mnist_maxout_example.py","link_basis":"harvester_set","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":"9a4cab9e77a16022"}},{"code_sha256_prefix":"7a3797969b03084e","entry":"create_weight_variable","repo":"philipperemy/tensorflow-maxout","repo_kind":"listed","path":"mnist_maxout_example.py","file_url":"https://github.com/philipperemy/tensorflow-maxout/blob/HEAD/mnist_maxout_example.py","link_basis":"harvester_set","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":"7a3797969b03084e"}},{"code_sha256_prefix":"b7a8162db3a2edfb","entry":"max_out","repo":"philipperemy/tensorflow-maxout","repo_kind":"listed","path":"maxout.py","file_url":"https://github.com/philipperemy/tensorflow-maxout/blob/HEAD/maxout.py","link_basis":"harvester_set","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":"b7a8162db3a2edfb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}