Methods › General › Activation Functions › SiLU
Sigmoid Linear Unit
SiLU
Introduced by Stefan Elfwing et al. in Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
** Sigmoid Linear Units, or SiLUs**, are activation functions for neural networks. The activation of the SiLU is computed by the sigmoid function multiplied by its input, or xσ(x).
See Gaussian Error Linear Units (GELUs) where the SiLU was originally coined, and see Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning and Swish: a Self-Gated Activation Function where the SiLU was experimented with later.
In Syntology name not resolved (unknown_name). The lookup matched no method, paper or venue by this name; that asserts nothing about whether code exists.
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 30 · with a code link: 16 · where Syntology ran a sample: 5 (4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (5 of 30 tagged: 4 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 30 of 30, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
MVNet: Hyperspectral Remote Sensing Image Classification Based on Hybrid Mamba-Transformer Vision Backbone Architecture 6 Jul 2025 · 1 repository · arXiv:2507.04409
-
Deriving Activation Functions Using Integration 20 Nov 2024 · 1 repository · arXiv:2411.13010
-
Sparsing Law: Towards Large Language Models with Greater Activation Sparsity 4 Nov 2024 · 1 repository · arXiv:2411.02335Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 5 harvested samples)
-
ActNAS : Generating Efficient YOLO Models using Activation NAS 11 Oct 2024 · 0 repositories · arXiv:2410.10887
-
UnSeGArmaNet: Unsupervised Image Segmentation using Graph Neural Networks with Convolutional ARMA Filters 8 Oct 2024 · 1 repository · arXiv:2410.06114
-
BrainTransformers: SNN-LLM 3 Oct 2024 · 0 repositories · arXiv:2410.14687
-
Efficient Privacy-Preserving KAN Inference Using Homomorphic Encryption 12 Sep 2024 · 0 repositories · arXiv:2409.07751
-
CipherDM: Secure Three-Party Inference for Diffusion Model Sampling 9 Sep 2024 · 0 repositories · arXiv:2409.05414
-
On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic 30 Aug 2024 · 0 repositories · arXiv:2409.00297
-
Reducing Fine-Tuning Memory Overhead by Approximate and Memory-Sharing Backpropagation 24 Jun 2024 · 1 repository · arXiv:2406.16282Syntology official (archive's flag): 10 ran · 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 8 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 11 unverified (of 21 harvested samples) · 3 pointer-only (licence)
-
Expanded Gating Ranges Improve Activation Functions 25 May 2024 · 0 repositories · arXiv:2405.20768
-
Stable and Robust Deep Learning By Hyperbolic Tangent Exponential Linear Unit (TeLU) 5 Feb 2024 · 0 repositories · arXiv:2402.02790
-
Leveraging Continuously Differentiable Activation Functions for Learning in Quantized Noisy Environments 4 Feb 2024 · 1 repository · arXiv:2402.02593
-
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models 6 Oct 2023 · 1 repository · arXiv:2310.04564
-
Learnable Extended Activation Function (LEAF) for Deep Neural Networks 30 Sep 2023 · 1 repository
-
Attention-Only Transformers and Implementing MLPs with Attention Heads 15 Sep 2023 · 0 repositories · arXiv:2309.08593
-
Compact: Approximating Complex Activation Functions for Secure Computation 9 Sep 2023 · 1 repository · arXiv:2309.04664
-
Deep Contract Design via Discontinuous Networks 5 Jul 2023 · 0 repositories · arXiv:2307.02318
-
Demystifying Oversmoothing in Attention-Based Graph Neural Networks 25 May 2023 · 0 repositories · arXiv:2305.16102
-
Saturated Non-Monotonic Activation Functions 12 May 2023 · 0 repositories · arXiv:2305.07537
-
Trainable Activations for Image Classification 26 Jan 2023 · 1 repository
-
Optimizing Anchor-based Detectors for Autonomous Driving Scenes 11 Aug 2022 · 0 repositories · arXiv:2208.06062
-
Adaptive hybrid activation function for deep neural networks 25 Apr 2022 · 1 repository
-
A Unified and Constructive Framework for the Universality of Neural Networks 30 Dec 2021 · 0 repositories · arXiv:2112.14877
-
AGGLIO: Global Optimization for Locally Convex Functions 6 Nov 2021 · 1 repository · arXiv:2111.03932
-
Simple Training Strategies and Model Scaling for Object Detection 30 Jun 2021 · 1 repository · arXiv:2107.00057
-
Low Curvature Activations Reduce Overfitting in Adversarial Training 15 Feb 2021 · 1 repository · arXiv:2102.07861Syntology official: no sample here; runs from other or unrecorded repositories · 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) · 1 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
Bottleneck Transformers for Visual Recognition 27 Jan 2021 · 13 repositories · arXiv:2101.11605Syntology 26 ran (of which 9 constructed an object rather than computing a result; 19 with no instrument failure: 1 honoured, 0 violated, 18 with no contract checked; 7 where Syntology's instrument failed) · 23 unverified (of 49 harvested samples) · 8 pointer-only (licence)
-
Searching for Activation Functions 16 Oct 2017 · 22 repositories · arXiv:1710.05941Syntology 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 (of 20 harvested samples) · 4 pointer-only (licence)
-
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning 10 Feb 2017 · 0 repositories · arXiv:1702.03118
Tasks archive 2025-07-28
20 shown of 41 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
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