Methods › General › Activation Functions › ELU

Exponential Linear Unit

ELU

44 papers tagged archive 2025-07-28

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

Source: Fast and Accurate Deep Network Learning by Exponential...See Code · pytorch/pytorch

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.

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.

TaskPapers
Deep Learning5
Image Classification4
General Classification3
image-classification3
Classification2
Decoder2
Multi-Task Learning2
Object2
Object Discovery2
Representation Learning2
Semantic Segmentation2
Computational Efficiency1
Contrastive Learning1
Deep Reinforcement Learning1
Denoising1
Electroencephalogram (EEG)1
Ensemble Learning1
Federated Learning1
GPU1
Graph Learning1

Usage over time archive 2025-07-28

Papers per year tagged with ELU: 2015 to 2025, peak 8 8 0 2015: 1 paper 2015 2016: 2 papers 2016 2017: 4 papers 2017 2018: 4 papers 2018 2019: 4 papers 2019 2020: 6 papers 2020 2021: 8 papers 2021 2022: 5 papers 2022 2023: 2 papers 2023 2024: 5 papers 2024 2025: 3 papers 2025
Papers per year the archive tags with this method, by the paper's archive date (44 dated). Bars are counts, not a trend claim.

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

Activation Functions

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