{"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/binarized-neural-networks","title":"Binarized Neural Networks","arxiv_id":"1602.02505","date":"2016-02-08","proceeding":"NeurIPS 2016 12","authors":["Itay Hubara","Daniel Soudry","Ran El Yaniv"],"abstract":"We introduce a method to train Binarized Neural Networks (BNNs) - neural\nnetworks with binary weights and activations at run-time and when computing the\nparameters' gradient at train-time. We conduct two sets of experiments, each\nbased on a different framework, namely Torch7 and Theano, where we train BNNs\non MNIST, CIFAR-10 and SVHN, and achieve nearly state-of-the-art results.\nDuring the forward pass, BNNs drastically reduce memory size and accesses, and\nreplace most arithmetic operations with bit-wise operations, which might lead\nto a great increase in power-efficiency. Last but not least, we wrote a binary\nmatrix multiplication GPU kernel with which it is possible to run our MNIST BNN\n7 times faster than with an unoptimized GPU kernel, without suffering any loss\nin classification accuracy. The code for training and running our BNNs is\navailable.","url_abs":"http://arxiv.org/abs/1602.02505v3","url_pdf":"http://arxiv.org/pdf/1602.02505v3.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":"binarized-neural-networks","repo_url":"https://github.com/itayhubara/BinaryNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"torch","reach":{"status":"ok"}},{"paper_slug":"binarized-neural-networks","repo_url":"https://github.com/ryuz/BinaryBrain","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}