{"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/batch-normalized-maxout-network-in-network","title":"Batch-normalized Maxout Network in Network","arxiv_id":"1511.02583","date":"2015-11-09","proceeding":null,"authors":["Jia-Ren Chang","Yong-Sheng Chen"],"abstract":"This paper reports a novel deep architecture referred to as Maxout network In\nNetwork (MIN), which can enhance model discriminability and facilitate the\nprocess of information abstraction within the receptive field. The proposed\nnetwork adopts the framework of the recently developed Network In Network\nstructure, which slides a universal approximator, multilayer perceptron (MLP)\nwith rectifier units, to exact features. Instead of MLP, we employ maxout MLP\nto learn a variety of piecewise linear activation functions and to mediate the\nproblem of vanishing gradients that can occur when using rectifier units.\nMoreover, batch normalization is applied to reduce the saturation of maxout\nunits by pre-conditioning the model and dropout is applied to prevent\noverfitting. Finally, average pooling is used in all pooling layers to\nregularize maxout MLP in order to facilitate information abstraction in every\nreceptive field while tolerating the change of object position. Because average\npooling preserves all features in the local patch, the proposed MIN model can\nenforce the suppression of irrelevant information during training. Our\nexperiments demonstrated the state-of-the-art classification performance when\nthe MIN model was applied to MNIST, CIFAR-10, and CIFAR-100 datasets and\ncomparable performance for SVHN dataset.","url_abs":"http://arxiv.org/abs/1511.02583v1","url_pdf":"http://arxiv.org/pdf/1511.02583v1.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":"batch-normalized-maxout-network-in-network","repo_url":"https://github.com/JohnBensen1000/machine_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"}],"methods":[{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"maxout","method_name":"Maxout"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"BNM NiN","rank_in_archive_order":175,"of":265,"metrics":{"Percentage correct":"93.3"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"BNM NiN","rank_in_archive_order":172,"of":211,"metrics":{"Percentage correct":"71.1"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"BNM NiN","rank_in_archive_order":10,"of":81,"metrics":{"Percentage error":"0.24"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-svhn","task":"Image Classification","dataset":"SVHN","model":"BNM NiN","rank_in_archive_order":22,"of":62,"metrics":{"Percentage error":"1.8"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1511.02583","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1511.02583"}},"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/JohnBensen1000/machine_learning","reach":null}],"summary":{"ran_draft_wrong":1,"ran_violates":1,"ran_fixture":1},"by_repo_kind":{"listed":{"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":"fc42e10c61720479","entry":"make_two_dimensional","repo":"JohnBensen1000/machine_learning","repo_kind":"listed","path":"maxoutCNN.py","file_url":"https://github.com/JohnBensen1000/machine_learning/blob/HEAD/maxoutCNN.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fc42e10c61720479"}},{"code_sha256_prefix":"5d33bc8a8ead5ba7","entry":"normalize","repo":"JohnBensen1000/machine_learning","repo_kind":"listed","path":"maxoutCNN.py","file_url":"https://github.com/JohnBensen1000/machine_learning/blob/HEAD/maxoutCNN.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5d33bc8a8ead5ba7"}},{"code_sha256_prefix":"78fdd4365700a723","entry":"sigmoid","repo":"JohnBensen1000/machine_learning","repo_kind":"listed","path":"maxoutCNN.py","file_url":"https://github.com/JohnBensen1000/machine_learning/blob/HEAD/maxoutCNN.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"78fdd4365700a723"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}