Papers › Deep convolutional tensor network

Deep convolutional tensor network

29 May 2020arXiv:2005.14506archive 2025-07-28

Philip Blagoveschensky, Anh Huy Phan

Neural networks have achieved state of the art results in many areas, supposedly due to parameter sharing, locality, and depth. Tensor networks (TNs) are linear algebraic representations of quantum many-body states based on their entanglement structure. TNs have found use in machine learning. We devise a novel TN based model called Deep convolutional tensor network (DCTN) for image classification, which has parameter sharing, locality, and depth. It is based on the Entangled plaquette states (EPS) TN. We show how EPS can be implemented as a backpropagatable layer. We test DCTN on MNIST, FashionMNIST, and CIFAR10 datasets. A shallow DCTN performs well on MNIST and FashionMNIST and has a small parameter count. Unfortunately, depth increases overfitting and thus decreases test accuracy. Also, DCTN of any depth performs badly on CIFAR10 due to overfitting. It is to be determined why. We discuss how the hyperparameters of DCTN affect its training and overfitting.

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 14 code samples harvested from 1 repository linked to this paper: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 10 ran (8 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.

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

philip-bl/dctn officialmentioned in papermentioned on GitHubpytorchSyntology: 14 samples, 10 ran (2 instrument-failed) · 4 unverified 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.

Code Syntology ran Syntology

14 samples harvested: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 4 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 · our draft was wrong
8ran
4unverified

Licence: 14 of the 14 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 philip-bl/dctn. “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.

philip-bl/dctn official repository 14 samples, 10 ran (2 instrument-failed) · 4 unverified
FromFileInitialization dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · abdd7d19b940edf7 · report fixture: returned FromFileInitialization · level recorded 2026-09-22
ManuallyChosenInitialization dctn/eps_plus_linear.py ran licence not identified · pointer only · 01c74d9e77e79894 · report fixture: returned ManuallyChosenInitialization · level recorded 2026-09-22
Pos2D dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2c88e5e8180314e4 · report fixture: returned Pos2D · level recorded 2026-09-22
RankOneTensorsBatch dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · ff308c58bcabddd4 · report fixture: returned RankOneTensorsBatch · level recorded 2026-09-22
UnitEmpiricalOutputStd dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · 2ec83a864af84843 · report fixture: returned UnitEmpiricalOutputStd · level recorded 2026-09-22
UnitTheoreticalOutputStd dctn/eps_plus_linear.py ran licence not identified · pointer only · 2f77d08733f11804 · report fixture: returned UnitTheoreticalOutputStd · level recorded 2026-09-22
ZeroCenteredNormalInitialization dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · 46fbd89cadb16869 · report fixture: returned ZeroCenteredNormalInitialization · level recorded 2026-09-22
ZeroCenteredUniformInitialization dctn/eps_plus_linear.py ran · metamorphic tier: deterministic licence not identified · pointer only · 58217b68f6f4b1a1 · report fixture: returned ZeroCenteredUniformInitialization · level recorded 2026-09-22
align in 23 papers dctn/eps_plus_linear.py ran · our draft was wrong licence not identified · pointer only · 79352edafa34095c · report fixture: signature input:tuple/1/Tensor, kernel_size:int/0/int · returned generator · level recorded 2026-09-22
align_with_positions dctn/eps_plus_linear.py ran · our draft was wrong licence not identified · pointer only · e02780e2bd5c6b38 · report fixture: signature input:tuple/1/Tensor, positions:tuple/1/Pos2D · returned generator · level recorded 2026-09-22
EPSesPlusLinear dctn/eps_plus_linear.py unverified licence not identified · pointer only · 6c81369e5c9bd656 · report
EPSesPlusLinear dctn/eps_plus_linear.py unverified licence not identified · pointer only · 41de4398ac825650 · report
make_windows dctn/eps_plus_linear.py unverified licence not identified · pointer only · 5557d1f4eb81e814 · report
make_windows dctn/eps_plus_linear.py unverified licence not identified · pointer only · b78a615943f60f64 · report

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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Deep convolutional tensor network (graph method: Deep convolutional tensor network). 12 bricks; individually on a fixture: 10 ran (of which 8 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

  1. EPSesPlusLinear entry · level 0 · unverified · 41de4398ac825650
  2. ManuallyChosenInitialization helper · level 1 · ran · 01c74d9e77e79894
  3. RankOneTensorsBatch helper · level 1 · ran · ff308c58bcabddd4
  4. UnitEmpiricalOutputStd helper · level 1 · ran · 2ec83a864af84843
  5. UnitTheoreticalOutputStd helper · level 1 · ran · 2f77d08733f11804
  6. ZeroCenteredNormalInitialization helper · level 1 · ran · 46fbd89cadb16869
  7. ZeroCenteredUniformInitialization helper · level 1 · ran · 58217b68f6f4b1a1
  8. make_windows helper · level 0 · unverified · b78a615943f60f64
  9. align helper · level 1 · ran · our draft was wrong · 79352edafa34095c
  10. Pos2D helper · level 1 · ran · 2c88e5e8180314e4
  11. align_with_positions helper · level 1 · ran · our draft was wrong · e02780e2bd5c6b38
  12. FromFileInitialization helper · level 1 · ran · abdd7d19b940edf7

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="2005.14506") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationTensor Networksimage-classification

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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