PSGU: Parametric self-circulation gating unit for deep neural networks
- 1 October 2021
- journal article
- research article
- Published by Elsevier in Journal of Visual Communication and Image Representation
- Vol. 80
Abstract
No abstract availableKeywords
Funding Information
- Beihang University
- National Natural Science Foundation of China (61671002)
This publication has 10 references indexed in Scilit:
- SPLASH: Learnable activation functions for improving accuracy and adversarial robustnessNeural Networks, 2021
- A survey on modern trainable activation functionsNeural Networks, 2021
- Ensemble of convolutional neural networks trained with different activation functionsExpert Systems with Applications, 2021
- PATS: A New Neural Network Activation Function with Parameter2020
- RMAF: Relu-Memristor-Like Activation Function for Deep LearningIEEE Access, 2020
- Improving deep neural network with Multiple Parametric Exponential Linear UnitsNeurocomputing, 2018
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- ImageNet Large Scale Visual Recognition ChallengeInternational Journal of Computer Vision, 2015
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997