Papers › Searching for Activation Functions

Searching for Activation Functions

16 Oct 2017ICLR 2018 1arXiv:1710.05941archive 2025-07-28

Prajit Ramachandran, Barret Zoph, Quoc V. Le

The choice of activation functions in deep networks has a significant effect on the training dynamics and task performance. Currently, the most successful and widely-used activation function is the Rectified Linear Unit (ReLU). Although various hand-designed alternatives to ReLU have been proposed, none have managed to replace it due to inconsistent gains. In this work, we propose to leverage automatic search techniques to discover new activation functions. Using a combination of exhaustive and reinforcement learning-based search, we discover multiple novel activation functions. We verify the effectiveness of the searches by conducting an empirical evaluation with the best discovered activation function. Our experiments show that the best discovered activation function, f(x) = x ·sigmoid(βx), which we name Swish, tends to work better than ReLU on deeper models across a number of challenging datasets. For example, simply replacing ReLUs with Swish units improves top-1 classification accuracy on ImageNet by 0.9% for Mobile NASNet-A and 0.6% for Inception-ResNet-v2. The simplicity of Swish and its similarity to ReLU make it easy for practitioners to replace ReLUs with Swish units in any neural network.

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 20 code samples harvested from 6 repositories linked to this paper: 13 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 20 samples from 6 repositories, 13 ran (8 with no instrument failure; 5 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 4 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

22 repositories listed; official and paper-mentioned ones first.

JacobM184/EfficientNet-for-Gun-detection mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (arXiv:1905.11946; that paper's own run record: 198 ran (of which 73 constructed an object rather than computing a result; 157 with no instrument failure: 26 honoured, 2 violated, 129 with no contract checked; 41 where Syntology's instrument failed) · 104 unverified); nothing checks that they implement this paper's method. report
KellyYutongHe/Knowledge-Distillation-Net-with-Swish mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Distilling the Knowledge in a Neural Network (arXiv:1503.02531; that paper's own run record: 23 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 0 violated, 8 with no contract checked; 9 where Syntology's instrument failed) · 14 unverified); nothing checks that they implement this paper's method. report
Neoanarika/CNN-using-Swish mentioned on GitHubtfSyntology: not harvested report
Neoanarika/Searching-for-activation-functions mentioned on GitHubtfMITSyntology: 6 samples, 3 ran (1 instrument-failed) · 3 unverified report
ShubAn1901/Licence-Plate-Recognition mentioned on GitHubpytorchSyntology: not harvested report
ShubAn1901/License-Plate-Recognition mentioned on GitHubpytorchSyntology: not harvested report
WarClans612/deep_learning_final mentioned on GitHubpytorchMITSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
WessZumino/expectation_propagation mentioned on GitHubtfApache-2.0Syntology: 8 samples, 5 ran (0 instrument-failed) · 3 unverified report
WessZumino/meanfield-theory-of-activation-functions mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
fengye-lu/PyTorch-SRGAN mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network (arXiv:1609.04802; that paper's own run record: 55 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 3 violated, 39 with no contract checked; 10 where Syntology's instrument failed) · 17 unverified); nothing checks that they implement this paper's method. report
islaterm/you-activated-my-neuron mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
jeyoor/pymich-dl mentioned on GitHubtfMITSyntology: not harvested report
jiajunhua/aitorzip-PyTorch-SRGAN mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
phogbinh/handwritten-digit-recognition mentioned on GitHubMITSyntology: not harvested report
swordgeek/SR mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
thomasbrandon/swish-torch mentioned on GitHubpytorchMITSyntology: not harvested report
tuantle/simple_nn_with_numpy mentioned on GitHubjaxMITSyntology: not harvested report
tyunist/memory_efficient_mish_swish mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
wnorowsb/Super-resolution-GAN mentioned on GitHubpytorchSyntology: not harvested report
wvabrinskas/Neuron mentioned on GitHubpytorchMITSyntology: not harvested report
Andy-Dang12/Activation-Functions pytorchMITSyntology: not harvested report
Westlake-AI/openmixup pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mixup: Beyond Empirical Risk Minimization (arXiv:1710.09412; that paper's own run record: 36 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 22 where Syntology's instrument failed) · 11 unverified), Visualizing the Loss Landscape of Neural Nets (arXiv:1712.09913; that paper's own run record: 3 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified), CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features (arXiv:1905.04899; that paper's own run record: 17 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. 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

20 samples harvested: 13 ran (of which 1 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 7 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.

3ran · our draft was wrong
2ran; the contract check could not run
8ran
7unverified

Licence: 4 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 6 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Neoanarika/Searching-for-activation-functions community (archive-listed) 6 samples, 3 ran (1 instrument-failed) · 3 unverified
fixed_padding in 28 papers src/childnetwork.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 5756d6bfbcce2dfc · report fixture: signature inputs:EagerTensor/4/float, kernel_size:int/0/int, data_format:str/0/str · returned EagerTensor · level recorded 2026-09-22
path_exists src/utils.py ran MIT (permissive) · e6085d661f8724f7 · report fixture: signature path:str/0/str, overwrite:bool/0/bool · returned str · level recorded 2026-09-26
remove_dir src/utils.py ran MIT (permissive) · 9e3b33e6b46657bb · report fixture: signature path:str/0/str · returned bool · level recorded 2026-09-26
batch_norm_relu in 5 papers src/childnetwork.py unverified MIT (permissive) · aad048324892b5d3 · report
conv2d_fixed_padding in 12 papers src/childnetwork.py unverified MIT (permissive) · c756a6986ed2d1b8 · report
relu_init src/utils.py unverified MIT (permissive) · c58c0528e0f0b05f · report
WarClans612/deep_learning_final community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
models.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 31117990d4f24fdf · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
fetch_public_key travis_pypi_setup.py unverified MIT (permissive) · 4fcc838ec7ac0111 · report
WessZumino/expectation_propagation community (archive-listed) 8 samples, 5 ran (0 instrument-failed) · 3 unverified
act in 30 papers Python/esp_utils.py ran Apache-2.0 (permissive) · f0ec10189ae424f4 · report fixture: signature h:ndarray/2/float, beta:float/0/float, activation:str/0/str · returned ndarray · level recorded 2026-09-26
epoch_sampling TF/analysis_utils.py ran fingerprinted Apache-2.0 (permissive) · 99c30c0e30d4744e · report fixture: signature epochs:int/0/int, uniform_step:int/0/int · returned list · level recorded 2026-09-26
index in 10 papers TF/analysis_utils.py ran Apache-2.0 (permissive) · 2bb7b02beb4bcb12 · report fixture: signature hessian_epoch:list/1/ndarray · returned tuple · level recorded 2026-09-26
initialize_parameters Python/esp_utils.py ran Apache-2.0 (permissive) · 1c69a8fc3aa908af · report fixture: signature layers:list/1/int · returned dict · level recorded 2026-09-26
sigmoid in 216 papers
census: 36 implementations from 56 papers, 7 distinct outputs across 3 buckets, one shared input per bucket
Python/esp_utils.py ran fingerprinted Apache-2.0 (permissive) · 3b622bff5ce900a3 · report fixture: signature beta:float/0/float, h:ndarray/1/float · returned ndarray · level recorded 2026-09-26
create_placeholders TF/esp_tf_utils.py unverified Apache-2.0 (permissive) · 7bbbdebd2c04644f · report
initialize_parameters TF/esp_tf_utils.py unverified Apache-2.0 (permissive) · e1fff8e843c51c8e · report
one_hot_econding TF/esp_tf_utils.py unverified Apache-2.0 (permissive) · f5bbffdf347b2247 · report
WessZumino/meanfield-theory-of-activation-functions community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
act in 30 papers TF/esp_tf_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant Apache-2.0 (permissive) · df1af39a35cafa81 · report fixture: signature h:EagerTensor/2/float, beta:EagerTensor/0/float, activation:str/0/str · returned EagerTensor · level recorded 2026-09-22
islaterm/you-activated-my-neuron community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
sig in 5 papers src/neuron/activation_functions.py ran · our draft was wrong fingerprinted no licence file found · pointer only · f32504dbf9150ad6 · report fixture: signature t:Tensor/2/float · returned Tensor · level recorded 2026-09-22
swish in 258 papers
census: 14 implementations from 37 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/neuron/activation_functions.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 919aae7a4c5d1c1a · report fixture: signature t:Tensor/2/float, beta:float/0/float · returned Tensor · level recorded 2026-09-22
tyunist/memory_efficient_mish_swish community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Swish_func swish.py ran no licence file found · pointer only · 637511ceeecf1796 · report fixture: returned Swish_func · 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.

4 assemblies on this paper: 4 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

4 sibling assemblies for Swish (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Swish (graph method: Swish). 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 4 siblings

  1. act entry · level 1 · ran; the contract check could not run (RAISES) · df1af39a35cafa81

harvested Assembly for Swish (graph method: Swish). 2 bricks; individually on a fixture: 2 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; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 4 siblings

  1. swish entry · level 1 · ran · our draft was wrong · 919aae7a4c5d1c1a
  2. sig helper · level 1 · ran · our draft was wrong · f32504dbf9150ad6

harvested Assembly for Swish (graph method: Swish). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 4 siblings

  1. Swish_func entry · level 1 · ran · 637511ceeecf1796

harvested Assembly for Swish (graph method: Swish). 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 4 siblings

  1. swish entry · level 1 · ran · our draft was wrong · 31117990d4f24fdf

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="1710.05941") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ClassificationReinforcement Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

ReLUSiLUSigmoid Activation

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