{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1510.03009"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1510.03009\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1510.03009"},"call":"get_concepts_for_paper(arxiv_id=\"1510.03009\")"}],"by_repo":[{"repo":"hantek/BinaryConnect","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"MatthieuCourbariaux/BinaryConnect","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"2d99cff1076ec6cbc52bae8e804a48c3d964432c4bfe1eaa549d70ccdadb1e5f","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}