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.
Papers archive 2025-07-28
30 shown of 30, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
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 ran 1 of 5 samples · 4 unverified
-
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 ran 10 of 21 samples · 11 unverified
-
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 ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
-
Bottleneck Transformers for Visual Recognition 27 Jan 2021 · 13 repositories · arXiv:2101.11605Syntology ran 26 of 49 samples · 23 unverified · 8 pointer-only (licence)
-
Searching for Activation Functions 16 Oct 2017 · 22 repositories · arXiv:1710.05941Syntology ran 6 of 20 samples · 14 unverified · 3 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