{"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/rmdl-random-multimodel-deep-learning-for","title":"RMDL: Random Multimodel Deep Learning for Classification","arxiv_id":"1805.01890","date":"2018-05-03","proceeding":null,"authors":["Kamran Kowsari","Mojtaba Heidarysafa","Donald E. Brown","Kiana Jafari Meimandi","Laura E. Barnes"],"abstract":"The continually increasing number of complex datasets each year necessitates\never improving machine learning methods for robust and accurate categorization\nof these data. This paper introduces Random Multimodel Deep Learning (RMDL): a\nnew ensemble, deep learning approach for classification. Deep learning models\nhave achieved state-of-the-art results across many domains. RMDL solves the\nproblem of finding the best deep learning structure and architecture while\nsimultaneously improving robustness and accuracy through ensembles of deep\nlearning architectures. RDML can accept as input a variety data to include\ntext, video, images, and symbolic. This paper describes RMDL and shows test\nresults for image and text data including MNIST, CIFAR-10, WOS, Reuters, IMDB,\nand 20newsgroup. These test results show that RDML produces consistently better\nperformance than standard methods over a broad range of data types and\nclassification problems.","url_abs":"http://arxiv.org/abs/1805.01890v2","url_pdf":"http://arxiv.org/pdf/1805.01890v2.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":"rmdl-random-multimodel-deep-learning-for","repo_url":"https://github.com/kk7nc/RMDL","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"document-classification","task_name":"Document Classification"},{"task_slug":"face-recognition","task_name":"Face Recognition"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"hierarchical-text-classification-of-blurbs","task_name":"Hierarchical Text Classification of Blurbs (GermEval 2019)"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"multi-label-text-classification","task_name":"Multi-Label Text Classification"},{"task_slug":"unsupervised-pre-training","task_name":"Unsupervised Pre-training"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/hierarchical-text-classification-of-blurbs-1","task":"Hierarchical Text Classification of Blurbs (GermEval 2019)","dataset":"LOCAL DATASET","model":"RMDL (15 RDLs","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (%)":"90.79"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-cifar-10","task":"Image Classification","dataset":"CIFAR-10","model":"RMDL (30 RDLs)","rank_in_archive_order":194,"of":265,"metrics":{"Percentage correct":"91.21"},"uses_additional_data":false},{"leaderboard":"/sota/image-classification-on-mnist","task":"Image Classification","dataset":"MNIST","model":"RMDL (30 RDLs)","rank_in_archive_order":5,"of":81,"metrics":{"Accuracy":"99.82","Percentage error":"0.18"},"uses_additional_data":false},{"leaderboard":"/sota/text-classification-on-20news","task":"Text Classification","dataset":"20NEWS","model":"RMDL (15 RDLs)","rank_in_archive_order":6,"of":16,"metrics":{"Accuracy":"87.91"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-pre-training-on-measles","task":"Unsupervised Pre-training","dataset":"Measles","model":"RMDL","rank_in_archive_order":5,"of":5,"metrics":{"Accuracy (%)":"0.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-pre-training-on-uci-measles","task":"Unsupervised Pre-training","dataset":"UCI measles","model":"","rank_in_archive_order":1,"of":3,"metrics":{"Sensitivity":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-pre-training-on-uci-measles","task":"Unsupervised Pre-training","dataset":"UCI measles","model":"RMDL 3 RDLs","rank_in_archive_order":2,"of":3,"metrics":{"Sensitivity":"0.8739"},"uses_additional_data":false},{"leaderboard":"/sota/unsupervised-pre-training-on-uci-measles","task":"Unsupervised Pre-training","dataset":"UCI measles","model":"RMDL (30 RDLs)","rank_in_archive_order":3,"of":3,"metrics":{"Sensitivity (VEB)":"90.69"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}