ReCA: A Parametric ReLU Composite Activation Function
Not on the map. Why?
Abstract (arXiv)
Activation functions have been shown to affect the performance of deep neural networks significantly. While the Rectified Linear Unit (ReLU) remains the dominant choice in practice, the optimal activation function for deep neural networks remains an open research question. In this paper, we propose a novel parametric activation function, ReCA, based on ReLU, which has been shown to outperform all baselines on state-of-the-art datasets using different complex neural network architectures.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 15 references that are in the map. First posted on arXiv 11 Apr 2025.
Builds on
8 of 15 references.
References · 8
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
- 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,845
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2016Wide Residual Networkscited by 3,070
- 2015Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)cited by 1,070
- 2017Self-Normalizing Neural Networkscited by 598
Built on by
Not cited yet.