{"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/quantized-neural-networks-training-neural","title":"Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations","arxiv_id":"1609.07061","date":"2016-09-22","proceeding":null,"authors":["Itay Hubara","Matthieu Courbariaux","Daniel Soudry","Ran El-Yaniv","Yoshua Bengio"],"abstract":"We introduce a method to train Quantized Neural Networks (QNNs) --- neural\nnetworks with extremely low precision (e.g., 1-bit) weights and activations, at\nrun-time. At train-time the quantized weights and activations are used for\ncomputing the parameter gradients. During the forward pass, QNNs drastically\nreduce memory size and accesses, and replace most arithmetic operations with\nbit-wise operations. As a result, power consumption is expected to be\ndrastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and\nImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to\ntheir 32-bit counterparts. For example, our quantized version of AlexNet with\n1-bit weights and 2-bit activations achieves $51\\%$ top-1 accuracy. Moreover,\nwe quantize the parameter gradients to 6-bits as well which enables gradients\ncomputation using only bit-wise operation. Quantized recurrent neural networks\nwere tested over the Penn Treebank dataset, and achieved comparable accuracy as\ntheir 32-bit counterparts using only 4-bits. Last but not least, we programmed\na binary matrix multiplication GPU kernel with which it is possible to run our\nMNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering\nany loss in classification accuracy. The QNN code is available online.","url_abs":"http://arxiv.org/abs/1609.07061v1","url_pdf":"http://arxiv.org/pdf/1609.07061v1.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":"quantized-neural-networks-training-neural","repo_url":"https://github.com/CR-Ko/BinaryNet-Caffe2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"caffe2","reach":{"status":"ok"}},{"paper_slug":"quantized-neural-networks-training-neural","repo_url":"https://github.com/PIlotcnc/neural","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"quantized-neural-networks-training-neural","repo_url":"https://github.com/neuralmagic/sparseml","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"quantized-neural-networks-training-neural","repo_url":"https://github.com/neuralmagic/sparsify","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"quantized-neural-networks-training-neural","repo_url":"https://github.com/yashkant/ENAS-Quantized-Neural-Networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"grouped-convolution","method_name":"Grouped Convolution"},{"method_slug":"local-response-normalization","method_name":"Local Response Normalization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"softmax","method_name":"Softmax"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1609.07061","atlas_url":"https://app.syntology.ai/?focus=1609.07061","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1609.07061"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.07061"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.07061"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.07061\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"1609.07061"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1609.07061\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1609.07061"},"call":"get_concepts_for_paper(arxiv_id=\"1609.07061\")"}],"by_repo":[{"repo":"CR-Ko/BinaryNet-Caffe2","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PIlotcnc/neural","kind":"listed","samples":10,"ran":5,"instrument":0,"unverified":5},{"repo":"neuralmagic/sparseml","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2205.12452"],"harvested_for_calls":[{"arxiv_id":"2205.12452","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2205.12452"},"call":"get_harvested_code_for_paper(arxiv_id=\"2205.12452\")"}]},{"repo":"neuralmagic/sparsify","kind":"listed","samples":2,"ran":1,"instrument":0,"unverified":1},{"repo":"yashkant/ENAS-Quantized-Neural-Networks","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/1609.07061.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/1609.07061.svg"},"claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neuralmagic/sparseml","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yashkant/ENAS-Quantized-Neural-Networks","reach":{"status":"unanswered"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/CR-Ko/BinaryNet-Caffe2","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/neuralmagic/sparsify","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PIlotcnc/neural","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":6,"unverified":6},"n_samples":12,"n_ran":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":6,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"listed":{"samples":12,"ran":6,"n_ran_checked":6,"n_instrument":0,"repositories":2}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":6,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-26","last":"2026-09-26","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"64dc20dca8882db2","code_sha256_prefix":"64dc20dca8882db2","entry":"add_deploy_opts","repo":"neuralmagic/sparsify","repo_kind":"listed","path":"src/sparsify/cli/opts.py","file_url":"https://github.com/neuralmagic/sparsify/blob/HEAD/src/sparsify/cli/opts.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"f:callable/0/?","fixture_out_type":"function","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"64dc20dca8882db2"}},{"code_sha256":"fb67524ca6f08994","code_sha256_prefix":"fb67524ca6f08994","entry":"convert_example_to_features","repo":"PIlotcnc/neural","repo_kind":"listed","path":"integrations/transformers/run_distill_qa.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/integrations/transformers/run_distill_qa.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"example:dict/0/?, tokenizer:SimpleTokenizer/0/?, max_seq_length:int/0/int, doc_stride:int/0/int, max_query_length:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","code_page":"/code/convert-example-to-features","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"fb67524ca6f08994"}},{"code_sha256":"e73fc1a24af5a318","code_sha256_prefix":"e73fc1a24af5a318","entry":"detect_framework","repo":"PIlotcnc/neural","repo_kind":"listed","path":"src/sparseml/base.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/src/sparseml/base.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"item:Framework/0/?","fixture_out_type":"Framework","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e73fc1a24af5a318"}},{"code_sha256":"b05e6b10690ba830","code_sha256_prefix":"b05e6b10690ba830","entry":"drop_layers","repo":"PIlotcnc/neural","repo_kind":"listed","path":"integrations/transformers/run_distill_qa.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/integrations/transformers/run_distill_qa.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, layers_to_keep:int/0/int","fixture_out_type":"BertWrapper","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b05e6b10690ba830"}},{"code_sha256":"37057a7078af9a5d","code_sha256_prefix":"37057a7078af9a5d","entry":"get_kr_layer","repo":"PIlotcnc/neural","repo_kind":"listed","path":"utils/pytorch2keras.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/utils/pytorch2keras.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"kr_model:callable/0/?, kr_layer_name:str/0/str","fixture_out_type":"SimpleLayer","level_recorded_at":"2026-09-26T05:30:53.715539+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"37057a7078af9a5d"}},{"code_sha256":"0988e1f7835f94f8","code_sha256_prefix":"0988e1f7835f94f8","entry":"get_pytorch_name","repo":"PIlotcnc/neural","repo_kind":"listed","path":"utils/pytorch2keras.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/utils/pytorch2keras.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"kr_name:str/0/str, layer_mapping:dict/0/?","fixture_out_type":"str","level_recorded_at":"2026-09-26T04:29:16.584584+00:00","code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"0988e1f7835f94f8"}},{"code_sha256":"c55723df4fa1140d","code_sha256_prefix":"c55723df4fa1140d","entry":"add_data_opts","repo":"neuralmagic/sparsify","repo_kind":"listed","path":"src/sparsify/cli/opts.py","file_url":"https://github.com/neuralmagic/sparsify/blob/HEAD/src/sparsify/cli/opts.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"c55723df4fa1140d"}},{"code_sha256":"8c8865bf5862de8e","code_sha256_prefix":"8c8865bf5862de8e","entry":"execute_in_sparseml_framework","repo":"PIlotcnc/neural","repo_kind":"listed","path":"src/sparseml/base.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/src/sparseml/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8c8865bf5862de8e"}},{"code_sha256":"416986508915b636","code_sha256_prefix":"416986508915b636","entry":"get_version","repo":"PIlotcnc/neural","repo_kind":"listed","path":"src/sparseml/base.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/src/sparseml/base.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"416986508915b636"}},{"code_sha256":"6fe673c869d15b78","code_sha256_prefix":"6fe673c869d15b78","entry":"load_and_normalize_cifar10","repo":"PIlotcnc/neural","repo_kind":"listed","path":"integrations/keras/prune_resnet20.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/integrations/keras/prune_resnet20.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"6fe673c869d15b78"}},{"code_sha256":"181ade20c4851e11","code_sha256_prefix":"181ade20c4851e11","entry":"postprocess_qa_predictions","repo":"PIlotcnc/neural","repo_kind":"listed","path":"integrations/transformers/utils_qa.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/integrations/transformers/utils_qa.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/postprocess-qa-predictions","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"181ade20c4851e11"}},{"code_sha256":"b33c979ffa9d04b2","code_sha256_prefix":"b33c979ffa9d04b2","entry":"postprocess_qa_predictions_with_beam_search","repo":"PIlotcnc/neural","repo_kind":"listed","path":"integrations/transformers/utils_qa.py","file_url":"https://github.com/PIlotcnc/neural/blob/HEAD/integrations/transformers/utils_qa.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":"/code/postprocess-qa-predictions-with-beam-search","census":null,"licence":"Apache-2.0","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"b33c979ffa9d04b2"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"b40eeb9356cc62bac16cbcbfdf723e5d213fcf46624fa4bb804ff25bc5648f89","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}