{"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/the-relative-performance-of-ensemble-methods","title":"The Relative Performance of Ensemble Methods with Deep Convolutional Neural Networks for Image Classification","arxiv_id":"1704.01664","date":"2017-04-05","proceeding":null,"authors":["Cheng Ju","Aurélien Bibaut","Mark J. Van Der Laan"],"abstract":"Artificial neural networks have been successfully applied to a variety of\nmachine learning tasks, including image recognition, semantic segmentation, and\nmachine translation. However, few studies fully investigated ensembles of\nartificial neural networks. In this work, we investigated multiple widely used\nensemble methods, including unweighted averaging, majority voting, the Bayes\nOptimal Classifier, and the (discrete) Super Learner, for image recognition\ntasks, with deep neural networks as candidate algorithms. We designed several\nexperiments, with the candidate algorithms being the same network structure\nwith different model checkpoints within a single training process, networks\nwith same structure but trained multiple times stochastically, and networks\nwith different structure. In addition, we further studied the over-confidence\nphenomenon of the neural networks, as well as its impact on the ensemble\nmethods. Across all of our experiments, the Super Learner achieved best\nperformance among all the ensemble methods in this study.","url_abs":"http://arxiv.org/abs/1704.01664v1","url_pdf":"http://arxiv.org/pdf/1704.01664v1.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":"the-relative-performance-of-ensemble-methods","repo_url":"https://github.com/faizanahemad/facebook-hateful-memes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"},{"task_slug":"translation","task_name":"Translation"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1704.01664","atlas_url":"https://app.syntology.ai/?focus=1704.01664","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}