Papers › Learning both Weights and Connections for Efficient Neural Networks

Learning both Weights and Connections for Efficient Neural Networks

8 Jun 2015NeurIPS 2015arXiv:1506.02626archive 2025-07-28

Song Han, Jeff Pool, John Tran, William J. Dally

Neural networks are both computationally intensive and memory intensive, making them difficult to deploy on embedded systems. Also, conventional networks fix the architecture before training starts; as a result, training cannot improve the architecture. To address these limitations, we describe a method to reduce the storage and computation required by neural networks by an order of magnitude without affecting their accuracy by learning only the important connections. Our method prunes redundant connections using a three-step method. First, we train the network to learn which connections are important. Next, we prune the unimportant connections. Finally, we retrain the network to fine tune the weights of the remaining connections. On the ImageNet dataset, our method reduced the number of parameters of AlexNet by a factor of 9x, from 61 million to 6.7 million, without incurring accuracy loss. Similar experiments with VGG-16 found that the number of parameters can be reduced by 13x, from 138 million to 10.3 million, again with no loss of accuracy.

PaperPDFCodeCode Syntology ranMethod as code

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 8 code samples harvested from 3 repositories linked to this paper: 7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 3 repositories, 7 ran (5 with no instrument failure; 2 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 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ciodar/deep-compression mentioned on GitHubpytorchSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
lehduong/ginp mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pruning Filters for Efficient ConvNets (arXiv:1608.08710; that paper's own run record: 23 ran (of which 4 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 1 violated, 7 with no contract checked; 14 where Syntology's instrument failed) · 13 unverified); nothing checks that they implement this paper's method. report
lehduong/kesi mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Paying more attention to snapshots of Iterative Pruning: Improving Model Compression... (arXiv:2006.11487; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
songhan/Deep-Compression-AlexNet mentioned on GitHubcaffe2BSD-2-ClauseSyntology: not harvested report
songhan/SqueezeNet-Deep-Compression mentioned on GitHubcaffe2Syntology: not harvested report
tomshalini/pruning_lenet300-100 mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
JoseVillagranE/Learning-Both-Weights-and-Connections-for-Efficient-NNs pytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
intellabs/model-compression-research-package pytorchnot reachable when probed 2026-09-17 — repositories for recent papers often appear after camera-readySyntology: 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

8 samples harvested: 7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
2ran; the contract check could not run
3ran
1unverified

Licence: 3 of the 8 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 3 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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

ciodar/deep-compression community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
LinearWithAdjustableDropout trainer/callbacks/pruning.py ran · metamorphic tier: deterministic MIT (permissive) · 6564e1ebcafd6d0f · report fixture: returned LinearWithAdjustableDropout · level recorded 2026-09-22
ThresholdPruning trainer/callbacks/pruning.py ran MIT (permissive) · f6511a3e3fdf9486 · report fixture: returned ThresholdPruning · level recorded 2026-09-22
get_pruned trainer/callbacks/pruning.py ran · honoured contract MIT (permissive) · 34f00aaf868661c9 · report fixture: signature module:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-22
sparsity_stats trainer/callbacks/pruning.py ran · honoured contract MIT (permissive) · fe8133bc905d6833 · report fixture: signature model:callable/0/?, name:str/0/str · returned tuple · level recorded 2026-09-22
IterativePruning trainer/callbacks/pruning.py unverified MIT (permissive) · 377845318c40391f · report
tomshalini/pruning_lenet300-100 community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
prune_weights prune_model.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 9def416438747df0 · report fixture: signature weight_list:ndarray/3/float, pruning_rate:float/0/float · returned ndarray · level recorded 2026-09-22
JoseVillagranE/Learning-Both-Weights-and-Connections-for-Efficient-NNs community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
FineGrainedPruner pruning.py ran no licence file found · pointer only · cdf35d1cd84c892d · report fixture: returned FineGrainedPruner · level recorded 2026-09-22
fine_grained_prune pruning.py ran; the contract check could not run (RAISES) no licence file found · pointer only · 57df211eb79a4f38 · report fixture: signature tensor:Tensor/2/float, sparsity:float/0/float · returned Tensor · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

3 assemblies on this paper: 3 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

3 sibling assemblies for Learning both Weights and Connections (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Learning both Weights and Connections (graph method: Learning both Weights and Connections). 5 bricks; individually on a fixture: 4 ran (of which 2 constructed an object rather than computing a result; 4 with no instrument failure: 2 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. IterativePruning entry · level 0 · unverified · 377845318c40391f
  2. LinearWithAdjustableDropout helper · level 1 · ran · 6564e1ebcafd6d0f
  3. ThresholdPruning helper · level 1 · ran · f6511a3e3fdf9486
  4. sparsity_stats metric · level 1 · ran · honoured contract · fe8133bc905d6833
  5. get_pruned metric · level 1 · ran · honoured contract · 34f00aaf868661c9

harvested Assembly for Learning both Weights and Connections (graph method: Learning both Weights and Connections). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. FineGrainedPruner entry · level 1 · ran · cdf35d1cd84c892d
  2. fine_grained_prune helper · level 1 · ran; the contract check could not run (RAISES) · 57df211eb79a4f38

harvested Assembly for Learning both Weights and Connections (graph method: Learning both Weights and Connections). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 3 siblings

  1. prune_weights entry · level 1 · ran; the contract check could not run (RAISES) · 9def416438747df0

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1506.02626") returns these assemblies with each brick's role and wiring (how to connect).

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