Erfact And Pserf Nonmonotonic Smooth Trainable Activation Functions
ASecurity
**arXiv ID:** 2109.04386 **Authors:** Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey **Published:** 2021-09-09T16:17:38Z **Abstract:** An activation function is a crucial component of a neural network that introduces non-linearity in the network. The state-of-the-art performance of a neural network depends also on the perfect choice of an activation function. We propose two novel non-monotonic smooth trainable activation functions, called ErfAct and Pserf. Experiments su...
Installs into .claude/skills of the current project.
Sponsors
SSkills DirectorySkills Directory
Know which skills are safe — weekly.
SSkills DirectorySkills Directory
Is that skill safe to install?
Are you the author of Erfact And Pserf Nonmonotonic Smooth Trainable Activation Functions?
Add the live security badge to your README. It updates with every re-scan.
[](https://www.skillsdirectory.com/skills/hiyenwong-erfact-and-pserf-nonmonotonic-smooth-trainable-act)
# ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions
**arXiv ID:** 2109.04386
**Authors:** Koushik Biswas, Sandeep Kumar, Shilpak Banerjee, Ashish Kumar Pandey
**Published:** 2021-09-09T16:17:38Z
**Abstract:**
An activation function is a crucial component of a neural network that introduces non-linearity in the network. The state-of-the-art performance of a neural network depends also on the perfect choice of an activation function. We propose two novel non-monotonic smooth trainable activation functions, called ErfAct and Pserf. Experiments suggest that the proposed functions improve the network performance significantly compared to the widely used activations like ReLU, Swish, and Mish. Replacing ReLU by ErfAct and Pserf, we have 5.68% and 5.42% improvement for top-1 accuracy on Shufflenet V2 (2.0x) network in CIFAR100 dataset, 2.11% and 1.96% improvement for top-1 accuracy on Shufflenet V2 (2.0x) network in CIFAR10 dataset, 1.0%, and 1.0% improvement on mean average precision (mAP) on SSD300 model in Pascal VOC dataset.
## Skill Description
This skill is generated from the arXiv paper: ErfAct and Pserf: Non-monotonic Smooth Trainable Activation Functions (2109.04386).
## How to Use
[To be filled in by the user or by future automation]
## References
- [arXiv:2109.04386](http://arxiv.org/abs/2109.04386v4)
