Methods › General › Activation Functions › ELU
Exponential Linear Unit
ELU
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
The Exponential Linear Unit (ELU) is an activation function for neural networks. In contrast to ReLUs, ELUs have negative values which allows them to push mean unit activations closer to zero like batch normalization but with lower computational complexity. Mean shifts toward zero speed up learning by bringing the normal gradient closer to the unit natural gradient because of a reduced bias shift effect. While LReLUs and PReLUs have negative values, too, they do not ensure a noise-robust deactivation state. ELUs saturate to a negative value with smaller inputs and thereby decrease the forward propagated variation and information.
The exponential linear unit (ELU) with 0 < α is:
f(x) = x if x > 0 α(exp(x) − 1) if x ≤0
Papers archive 2025-07-28
30 shown of 44, 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.
-
PAUSE: Low-Latency and Privacy-Aware Active User Selection for Federated Learning 17 Mar 2025 · 1 repository · arXiv:2503.13173
-
Evaluating the Performance of TAAF for image classification models 13 Feb 2025 · 1 repository
-
Gompertz Linear Units: Leveraging Asymmetry for Enhanced Learning Dynamics 5 Feb 2025 · 1 repository · arXiv:2502.03654
-
Deriving Activation Functions Using Integration 20 Nov 2024 · 1 repository · arXiv:2411.13010
-
Enhancing the Influence of Labels on Unlabeled Nodes in Graph Convolutional Networks 4 Nov 2024 · 1 repository · arXiv:2411.02279
-
On Expressive Power of Quantized Neural Networks under Fixed-Point Arithmetic 30 Aug 2024 · 0 repositories · arXiv:2409.00297
-
SwishReLU: A Unified Approach to Activation Functions for Enhanced Deep Neural Networks Performance 11 Jul 2024 · 0 repositories · arXiv:2407.08232
-
Deep Multi-Task Learning for Malware Image Classification 9 May 2024 · 0 repositories · arXiv:2405.05906
-
TaLU: A Hybrid Activation Function Combining Tanh and Rectified Linear Unit to Enhance Neural Networks 8 May 2023 · 1 repository · arXiv:2305.04402
-
Ensemble Learning Model on Artificial Neural Network-Backpropagation (ANN-BP) Architecture for Coal Pillar Stability Classification 29 Mar 2023 · 0 repositories · arXiv:2303.16524
-
LMEC: Learnable Multiplicative Absolute Position Embedding Based Conformer for Speech Recognition 5 Dec 2022 · 1 repository · arXiv:2212.02099
-
SignReLU neural network and its approximation ability 19 Oct 2022 · 1 repository · arXiv:2210.10264
-
TEDL: A Two-stage Evidential Deep Learning Method for Classification Uncertainty Quantification 12 Sep 2022 · 0 repositories · arXiv:2209.05522
-
Constrained Monotonic Neural Networks 24 May 2022 · 2 repositories · arXiv:2205.11775
-
Beyond EM Algorithm on Over-specified Two-Component Location-Scale Gaussian Mixtures 23 May 2022 · 0 repositories · arXiv:2205.11078
-
A Unified and Constructive Framework for the Universality of Neural Networks 30 Dec 2021 · 0 repositories · arXiv:2112.14877
-
Reachability analysis of neural networks using mixed monotonicity 15 Nov 2021 · 1 repository · arXiv:2111.07683
-
Activation Functions in Deep Learning: A Comprehensive Survey and Benchmark 29 Sep 2021 · 1 repository · arXiv:2109.14545
-
PAUSE: Positive and Annealed Unlabeled Sentence Embedding 7 Sep 2021 · 1 repository · arXiv:2109.03155Syntology ran 2 of 2 samples · 0 unverified
-
Research on Optimization Method of Multi-scale Fish Target Fast Detection Network 11 Apr 2021 · 0 repositories · arXiv:2104.05050
-
Co-Adaptation of Algorithmic and Implementational Innovations in Inference-based Deep Reinforcement Learning 31 Mar 2021 · 1 repository · arXiv:2103.17258
-
Generalized Universal Approximation for Certified Networks 1 Jan 2021 · 0 repositories
-
TeLU: A New Activation Function for Deep Learning 1 Jan 2021 · 0 repositories
-
Comparisons among different stochastic selection of activation layers for convolutional neural networks for healthcare 24 Nov 2020 · 0 repositories · arXiv:2011.11834
-
Deep Multi-Task Learning for SSVEP Detection and Visual Response Mapping 10 Oct 2020 · 1 repository
-
Groove2Groove: One-Shot Music Style Transfer with Supervision from Synthetic Data 26 Aug 2020 · 1 repository
-
Reconstruction Bottlenecks in Object-Centric Generative Models 13 Jul 2020 · 1 repository · arXiv:2007.06245
-
Interval Universal Approximation for Neural Networks 12 Jul 2020 · 0 repositories · arXiv:2007.06093
-
Overcoming Overfitting and Large Weight Update Problem in Linear Rectifiers: Thresholded Exponential Rectified Linear Units 4 Jun 2020 · 0 repositories · arXiv:2006.02797
-
Spleeter: A Fast And State-of-the Art Music Source Separation Tool With Pre-trained Models 4 Nov 2019 · 3 repositories
Tasks archive 2025-07-28
20 shown of 59 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