Methods › General › Activation Functions › TanhExp
Tanh Exponential Activation Function
TanhExp
Introduced by Xinyu Liu et al. in TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
Lightweight or mobile neural networks used for real-time computer vision tasks contain fewer parameters than normal networks, which lead to a constrained performance. In this work, we proposed a novel activation function named Tanh Exponential Activation Function (TanhExp) which can improve the performance for these networks on image classification task significantly. The definition of TanhExp is f(x) = x tanh(eˣ). We demonstrate the simplicity, efficiency, and robustness of TanhExp on various datasets and network models and TanhExp outperforms its counterparts in both convergence speed and accuracy. Its behaviour also remains stable even with noise added and dataset altered. We show that without increasing the size of the network, the capacity of lightweight neural networks can be enhanced by TanhExp with only a few training epochs and no extra parameters added.
Papers archive 2025-07-28
5 shown of 5, 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.
-
Neural Density-Distance Fields 29 Jul 2022 · 1 repository · arXiv:2207.14455
-
TeLU: A New Activation Function for Deep Learning 1 Jan 2021 · 0 repositories
-
Smooth activations and reproducibility in deep networks 20 Oct 2020 · 4 repositories · arXiv:2010.09931Syntology ran 0 of 3 samples · 3 unverified
-
TanhSoft -- a family of activation functions combining Tanh and Softplus 8 Sep 2020 · 0 repositories · arXiv:2009.03863
-
TanhExp: A Smooth Activation Function with High Convergence Speed for Lightweight Neural Networks 22 Mar 2020 · 0 repositories · arXiv:2003.09855
Tasks archive 2025-07-28
7 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| Image Classification | 2 |
| Deep Learning | 1 |
| General Classification | 1 |
| NeRF | 1 |
| Novel View Synthesis | 1 |
| Visual Localization | 1 |
| image-classification | 1 |
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