Evaluating CNN with Oscillatory Activation Function
Not on the map. Why?
Abstract (arXiv)
The reason behind CNNs capability to learn high-dimensional complex features from the images is the non-linearity introduced by the activation function. Several advanced activation functions have been discovered to improve the training process of neural networks, as choosing an activation function is a crucial step in the modeling. Recent research has proposed using an oscillating activation function to solve classification problems inspired by the human brain cortex. This paper explores the performance of one of the CNN architecture ALexNet on MNIST and CIFAR10 datasets using oscillatory activation function (GCU) and some other commonly used activation functions like ReLu, PReLu, and Mish.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 10 of its 29 references that are in the map. First posted on arXiv 13 Nov 2022.
Builds on
10 of 29 references.
References · 10
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2014Going Deeper with Convolutionscited by 4,241
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,611
- 2020A survey on modern trainable activation functionscited by 89
- 2019Effective and Efficient Dropout for Deep Convolutional Neural Networkscited by 21
- 2018Learning Combinations of Activation Functionscited by 20
- 2020A Survey on Activation Functions and their relation with Xavier and He Normal Initializationcited by 13
- 2021Growing Cosine Unit: A Novel Oscillatory Activation Function That Can Speedup Training and Reduce Parameters in Convolutional Neural Networkscited by 13
- 2019Ensemble of Convolutional Neural Networks Trained with Different Activation Functionscited by 9
Built on by
Not cited yet.