Papers › Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers

Deep Learning without Shortcuts: Shaping the Kernel with Tailored Rectifiers

15 Mar 2022ICLR 2022 4arXiv:2203.08120archive 2025-07-28

Guodong Zhang, Aleksandar Botev, James Martens

Training very deep neural networks is still an extremely challenging task. The common solution is to use shortcut connections and normalization layers, which are both crucial ingredients in the popular ResNet architecture. However, there is strong evidence to suggest that ResNets behave more like ensembles of shallower networks than truly deep ones. Recently, it was shown that deep vanilla networks (i.e. networks without normalization layers or shortcut connections) can be trained as fast as ResNets by applying certain transformations to their activation functions. However, this method (called Deep Kernel Shaping) isn't fully compatible with ReLUs, and produces networks that overfit significantly more than ResNets on ImageNet. In this work, we rectify this situation by developing a new type of transformation that is fully compatible with a variant of ReLUs -- Leaky ReLUs. We show in experiments that our method, which introduces negligible extra computational cost, achieves validation accuracies with deep vanilla networks that are competitive with ResNets (of the same width/depth), and significantly higher than those obtained with the Edge of Chaos (EOC) method. And unlike with EOC, the validation accuracies we obtain do not get worse with depth.

PaperPDFConference PDFCodeCode 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 24 code samples harvested from 2 repositories linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 7 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 11 ran (9 with no instrument failure; 2 where Syntology's instrument failed); found in paper text by Syntology: 6 samples from 1 repository, 3 ran (1 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

deepmind/dks officialmentioned in paperjaxSyntology: 18 samples, 11 ran (2 instrument-failed) · 7 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

24 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 7 honoured, 2 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

7ran · honoured contract
2ran · violated contract
3ran · our draft was wrong
1ran; the contract check could not run
1ran
10unverified

Licence: 0 of the 24 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.

deepmind/dks official repository 18 samples, 11 ran (2 instrument-failed) · 7 unverified
_bentid dks/base/activation_transform.py ran fingerprinted Apache-2.0 (permissive) · b803f9baa24bfd4f · report fixture: signature x:ndarray/1/float · returned ndarray · level recorded 2026-09-22
_calc_c_curv dks/base/activation_transform.py ran · honoured contract Apache-2.0 (permissive) · 4a9bd4aba951f2ee · report fixture: signature activation:callable/0/?, c:float/0/float, q_output:float/0/float · returned float64 · level recorded 2026-09-22
_calc_c_slope dks/base/activation_transform.py ran · honoured contract Apache-2.0 (permissive) · af6685abaca2e383 · report fixture: signature activation:callable/0/?, c:float/0/float, q_output:float/0/float · returned float64 · level recorded 2026-09-22
_elu dks/base/activation_transform.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 66703fda3e8cfbe3 · report fixture: signature x:ndarray/1/float, a:float/0/float, l:float/0/float · returned ndarray · level recorded 2026-09-22
_estimate_2d_gaussian_mean dks/base/activation_transform.py ran · honoured contract Apache-2.0 (permissive) · b4a306c2c7f07155 · report fixture: signature fn:callable/0/? · returned float · level recorded 2026-09-22
_gelu dks/base/activation_transform.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · c8c394e2c6a1a2ce · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_gelu_exact dks/base/activation_transform.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 45c504b4c4b5cb39 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_get_roots_cache_file dks/base/activation_transform.py ran · our draft was wrong Apache-2.0 (permissive) · fecba24c85a8383c · report fixture: returned str · level recorded 2026-09-22
_softplus dks/base/activation_transform.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 8e18417d18243196 · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_swish dks/base/activation_transform.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 2c59e2c9e3970f5a · report fixture: signature x:ndarray/2/float · returned ndarray · level recorded 2026-09-22
_transform_activation dks/base/activation_transform.py ran · our draft was wrong Apache-2.0 (permissive) · 5afc010dc0e842f8 · report fixture: signature phi:callable/0/?, params:dict/0/? · returned function · level recorded 2026-09-22
_calc_c_map dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 3e9f86b459eecc31 · report
_calc_q_slope_1 dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 95c482d63878f89f · report
_compute_output_params dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 518f8f86235bcdf2 · report
_estimate_gaussian_mean dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 17cfc190249b5d4f · report
_leaky_relu dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 8bd5c8a0631e8f17 · report
_precompute_or_load_roots dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 9c3d8825878c6315 · report
_solve_for_activation_params dks/base/activation_transform.py unverified Apache-2.0 (permissive) · 95b55a581b4926c8 · report
deepmind/kfac_jax found in paper text by Syntology 6 samples, 3 ran (2 instrument-failed) · 3 unverified
broadcast_in_dim_equivalent kfac_jax/_src/tag_graph_matcher.py ran · violated contract Apache-2.0 (permissive) · 987e113518340066 · report fixture: signature equation1:MockJaxprEqn/0/?, equation2:MockJaxprEqn/0/? · returned bool · level recorded 2026-09-24
compatible_sum kfac_jax/_src/curvature_blocks/utils.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · dc1b986b1be917d4 · report fixture: signature tensor:ArrayImpl/4/float, target_shape:tuple/1/int, skip_axes:list/1/int · returned ArrayImpl · level recorded 2026-09-24
eval_jaxpr_eqn kfac_jax/_src/tag_graph_matcher.py ran · our draft was wrong Apache-2.0 (permissive) · 42474a82097165d1 · report fixture: signature eqn:MockJaxprEqn/0/?, in_values:list/1/ArrayImpl · returned list · level recorded 2026-09-24
get_and_verify_loss_meta kfac_jax/_src/layers_and_loss_tags.py unverified Apache-2.0 (permissive) · 14e10e479569a361 · report
get_loss_outputs kfac_jax/_src/layers_and_loss_tags.py unverified Apache-2.0 (permissive) · b4a5e9703e6605e1 · report
reshape_equivalent kfac_jax/_src/tag_graph_matcher.py unverified Apache-2.0 (permissive) · ee339b16cfba7ff0 · 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 Kernel Shaping with tailored rectifiers (graph method: Deep Kernel Shaping with tailored rectifiers). 18 bricks; individually on a fixture: 11 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 7 honoured, 1 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified. The assembly has not been run end-to-end.

  1. _solve_for_activation_params entry · level 0 · unverified · 95b55a581b4926c8
  2. _calc_c_curv helper · level 1 · ran · honoured contract · 4a9bd4aba951f2ee
  3. _calc_c_slope helper · level 1 · ran · honoured contract · af6685abaca2e383
  4. _calc_q_slope_1 helper · level 0 · unverified · 95c482d63878f89f
  5. _compute_output_params helper · level 0 · unverified · 518f8f86235bcdf2
  6. _transform_activation helper · level 1 · ran · our draft was wrong · 5afc010dc0e842f8
  7. _calc_c_map helper · level 0 · unverified · 3e9f86b459eecc31
  8. _estimate_gaussian_mean helper · level 0 · unverified · 17cfc190249b5d4f
  9. _estimate_2d_gaussian_mean helper · level 1 · ran · honoured contract · b4a306c2c7f07155
  10. _precompute_or_load_roots helper · level 0 · unverified · 9c3d8825878c6315
  11. _get_roots_cache_file helper · level 1 · ran · our draft was wrong · fecba24c85a8383c
  12. _bentid helper · level 1 · ran · b803f9baa24bfd4f
  13. _elu helper · level 1 · ran · violated contract · 66703fda3e8cfbe3
  14. _gelu helper · level 1 · ran · honoured contract · c8c394e2c6a1a2ce
  15. _gelu_exact helper · level 1 · ran · honoured contract · 45c504b4c4b5cb39
  16. _leaky_relu helper · level 0 · unverified · 8bd5c8a0631e8f17
  17. _softplus helper · level 1 · ran · honoured contract · 8e18417d18243196
  18. _swish helper · level 1 · ran · honoured contract · 2c59e2c9e3970f5a

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="2203.08120") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Deep Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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