Oscillating activation functions can improve the performance of convolutional neural networks
- 11 April 2025
- journal article
- Published by Elsevier in Applied Soft Computing
- Vol. 175
Abstract
No abstract availableThis publication has 13 references indexed in Scilit:
- Biologically inspired oscillating activation functions can bridge the performance gap between biological and artificial neuronsExpert Systems with Applications, 2024
- KAF + RSigELU: a nonlinear and kernel-based activation function for deep neural networksNeural Computing and Applications, 2022
- Improving deep neural network with Multiple Parametric Exponential Linear UnitsNeurocomputing, 2018
- Deep neural networks with Elastic Rectified Linear Units for object recognitionNeurocomputing, 2018
- Randomly translational activation inspired by the input distributions of ReLUNeurocomputing, 2018
- Neural network with unbounded activation functions is universal approximatorApplied and Computational Harmonic Analysis, 2017
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- Solving the XOR problem and the detection of symmetry using a single complex-valued neuronNeural Networks, 2003
- Pyramidal Neuron as Two-Layer Neural NetworkNeuron, 2003
- Learning representations by back-propagating errorsNature, 1986