{"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/multi-residual-networks-improving-the-speed","title":"Multi-Residual Networks: Improving the Speed and Accuracy of Residual Networks","arxiv_id":"1609.05672","date":"2016-09-19","proceeding":null,"authors":["Masoud Abdi","Saeid Nahavandi"],"abstract":"In this article, we take one step toward understanding the learning behavior\nof deep residual networks, and supporting the observation that deep residual\nnetworks behave like ensembles. We propose a new convolutional neural network\narchitecture which builds upon the success of residual networks by explicitly\nexploiting the interpretation of very deep networks as an ensemble. The\nproposed multi-residual network increases the number of residual functions in\nthe residual blocks. Our architecture generates models that are wider, rather\nthan deeper, which significantly improves accuracy. We show that our model\nachieves an error rate of 3.73% and 19.45% on CIFAR-10 and CIFAR-100\nrespectively, that outperforms almost all of the existing models. We also\ndemonstrate that our model outperforms very deep residual networks by 0.22%\n(top-1 error) on the full ImageNet 2012 classification dataset. Additionally,\ninspired by the parallel structure of multi-residual networks, a model\nparallelism technique has been investigated. The model parallelism method\ndistributes the computation of residual blocks among the processors, yielding\nup to 15% computational complexity improvement.","url_abs":"http://arxiv.org/abs/1609.05672v4","url_pdf":"http://arxiv.org/pdf/1609.05672v4.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":"multi-residual-networks-improving-the-speed","repo_url":"https://github.com/masoudabd/multi-resnet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"torch","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}