Back to Search
Start Over
Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications.
- Source :
- CMES-Computer Modeling in Engineering & Sciences; 2019, Vol. 118 Issue 1, p1-14, 14p
- Publication Year :
- 2019
-
Abstract
- The nonlinear activation functions in the deep CNN (Convolutional Neural Network) based on fluid dynamics are presented. We propose two types of activation functions by applying the so-called parametric softsign to the negative region. We use significantly the well-known TensorFlow as the deep learning framework. The CNN architecture consists of three convolutional layers with the max-pooling and one fullyconnected softmax layer. The CNN approaches are applied to three benchmark datasets, namely, MNIST, CIFAR-10, and CIFAR-100. Numerical results demonstrate the workability and the validity of the present approach through comparison with other numerical performances. [ABSTRACT FROM AUTHOR]
- Subjects :
- NEURAL computers
FLUID dynamics
BIG data
NUMERICAL analysis
MACHINE learning
Subjects
Details
- Language :
- English
- ISSN :
- 15261492
- Volume :
- 118
- Issue :
- 1
- Database :
- Complementary Index
- Journal :
- CMES-Computer Modeling in Engineering & Sciences
- Publication Type :
- Academic Journal
- Accession number :
- 134291199
- Full Text :
- https://doi.org/10.31614/cmes.2019.04676