{"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/neural-networks-with-few-multiplications","title":"Neural Networks with Few Multiplications","arxiv_id":"1510.03009","date":"2015-10-11","proceeding":null,"authors":["Zhouhan Lin","Matthieu Courbariaux","Roland Memisevic","Yoshua Bengio"],"abstract":"For most deep learning algorithms training is notoriously time consuming.\nSince most of the computation in training neural networks is typically spent on\nfloating point multiplications, we investigate an approach to training that\neliminates the need for most of these. Our method consists of two parts: First\nwe stochastically binarize weights to convert multiplications involved in\ncomputing hidden states to sign changes. Second, while back-propagating error\nderivatives, in addition to binarizing the weights, we quantize the\nrepresentations at each layer to convert the remaining multiplications into\nbinary shifts. Experimental results across 3 popular datasets (MNIST, CIFAR10,\nSVHN) show that this approach not only does not hurt classification performance\nbut can result in even better performance than standard stochastic gradient\ndescent training, paving the way to fast, hardware-friendly training of neural\nnetworks.","url_abs":"http://arxiv.org/abs/1510.03009v3","url_pdf":"http://arxiv.org/pdf/1510.03009v3.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":"neural-networks-with-few-multiplications","repo_url":"https://github.com/hantek/BinaryConnect","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}},{"paper_slug":"neural-networks-with-few-multiplications","repo_url":"https://github.com/MatthieuCourbariaux/BinaryConnect","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"GPL-2.0"}}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1510.03009","atlas_url":"https://app.syntology.ai/?focus=1510.03009","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}