{"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/improving-deep-neural-networks-with","title":"Improving Deep Neural Networks with Probabilistic Maxout Units","arxiv_id":"1312.6116","date":"2013-12-20","proceeding":null,"authors":["Jost Tobias Springenberg","Martin Riedmiller"],"abstract":"We present a probabilistic variant of the recently introduced maxout unit.\nThe success of deep neural networks utilizing maxout can partly be attributed\nto favorable performance under dropout, when compared to rectified linear\nunits. It however also depends on the fact that each maxout unit performs a\npooling operation over a group of linear transformations and is thus partially\ninvariant to changes in its input. Starting from this observation we ask the\nquestion: Can the desirable properties of maxout units be preserved while\nimproving their invariance properties ? We argue that our probabilistic maxout\n(probout) units successfully achieve this balance. We quantitatively verify\nthis claim and report classification performance matching or exceeding the\ncurrent state of the art on three challenging image classification benchmarks\n(CIFAR-10, CIFAR-100 and SVHN).","url_abs":"http://arxiv.org/abs/1312.6116v2","url_pdf":"http://arxiv.org/pdf/1312.6116v2.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":[],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"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":"DNN+Probabilistic Maxout","rank_in_archive_order":202,"of":265,"metrics":{"Percentage correct":"90.6"},"uses_additional_data":true},{"leaderboard":"/sota/image-classification-on-cifar-100","task":"Image Classification","dataset":"CIFAR-100","model":"DNN+Probabilistic Maxout","rank_in_archive_order":195,"of":211,"metrics":{"Percentage correct":"61.9"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}