Papers › Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activations

22 Sep 2016arXiv:1609.07061archive 2025-07-28

Itay Hubara, Matthieu Courbariaux, Daniel Soudry, Ran El-Yaniv, Yoshua Bengio

We introduce a method to train Quantized Neural Networks (QNNs) --- neural networks with extremely low precision (e.g., 1-bit) weights and activations, at run-time. At train-time the quantized weights and activations are used for computing the parameter gradients. During the forward pass, QNNs drastically reduce memory size and accesses, and replace most arithmetic operations with bit-wise operations. As a result, power consumption is expected to be drastically reduced. We trained QNNs over the MNIST, CIFAR-10, SVHN and ImageNet datasets. The resulting QNNs achieve prediction accuracy comparable to their 32-bit counterparts. For example, our quantized version of AlexNet with 1-bit weights and 2-bit activations achieves 51% top-1 accuracy. Moreover, we quantize the parameter gradients to 6-bits as well which enables gradients computation using only bit-wise operation. Quantized recurrent neural networks were tested over the Penn Treebank dataset, and achieved comparable accuracy as their 32-bit counterparts using only 4-bits. Last but not least, we programmed a binary matrix multiplication GPU kernel with which it is possible to run our MNIST QNN 7 times faster than with an unoptimized GPU kernel, without suffering any loss in classification accuracy. The QNN code is available online.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 12 code samples harvested from 2 repositories linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 12 samples from 2 repositories, 6 ran (6 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

CR-Ko/BinaryNet-Caffe2 mentioned on GitHubcaffe2Syntology: not harvested report
PIlotcnc/neural mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 5 ran (0 instrument-failed) · 5 unverified report
neuralmagic/sparseml mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sparse*BERT: Sparse Models Generalize To New tasks and Domains (arXiv:2205.12452; that paper's own run record: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
neuralmagic/sparsify mentioned on GitHubtfApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
yashkant/ENAS-Quantized-Neural-Networks mentioned on GitHubtfSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

12 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

6ran
6unverified

Licence: 0 of the 12 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives 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” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: 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. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

PIlotcnc/neural community (archive-listed) 10 samples, 5 ran (0 instrument-failed) · 5 unverified
convert_example_to_features in 10 papers integrations/transformers/run_distill_qa.py ran Apache-2.0 (permissive) · fb67524ca6f08994 · report fixture: signature example:dict/0/?, tokenizer:SimpleTokenizer/0/?, max_seq_length:int/0/int, doc_stride:int/0/int, max_query_length:int/0/int · returned tuple · level recorded 2026-09-26
detect_framework src/sparseml/base.py ran Apache-2.0 (permissive) · e73fc1a24af5a318 · report fixture: signature item:Framework/0/? · returned Framework · level recorded 2026-09-26
drop_layers integrations/transformers/run_distill_qa.py ran Apache-2.0 (permissive) · b05e6b10690ba830 · report fixture: signature model:callable/0/?, layers_to_keep:int/0/int · returned BertWrapper · level recorded 2026-09-26
get_kr_layer utils/pytorch2keras.py ran Apache-2.0 (permissive) · 37057a7078af9a5d · report fixture: signature kr_model:callable/0/?, kr_layer_name:str/0/str · returned SimpleLayer · level recorded 2026-09-26
get_pytorch_name utils/pytorch2keras.py ran Apache-2.0 (permissive) · 0988e1f7835f94f8 · report fixture: signature kr_name:str/0/str, layer_mapping:dict/0/? · returned str · level recorded 2026-09-26
execute_in_sparseml_framework src/sparseml/base.py unverified Apache-2.0 (permissive) · 8c8865bf5862de8e · report
get_version src/sparseml/base.py unverified Apache-2.0 (permissive) · 416986508915b636 · report
load_and_normalize_cifar10 integrations/keras/prune_resnet20.py unverified Apache-2.0 (permissive) · 6fe673c869d15b78 · report
postprocess_qa_predictions in 10 papers integrations/transformers/utils_qa.py unverified Apache-2.0 (permissive) · 181ade20c4851e11 · report
postprocess_qa_predictions_with_beam_search in 10 papers integrations/transformers/utils_qa.py unverified Apache-2.0 (permissive) · b33c979ffa9d04b2 · report
neuralmagic/sparsify community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
add_deploy_opts src/sparsify/cli/opts.py ran Apache-2.0 (permissive) · 64dc20dca8882db2 · report fixture: signature f:callable/0/? · returned function · level recorded 2026-09-26
add_data_opts src/sparsify/cli/opts.py unverified Apache-2.0 (permissive) · c55723df4fa1140d · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionConvolutionDense ConnectionsDropoutGrouped ConvolutionLocal Response NormalizationMax PoolingReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections