Nonlinear Activation Functions in CNN Based on Fluid Dynamics and Its Applications

• 作者: Kazuhiko Kakuda Shinichiro Miura Tomoyuki Enomoto
• 来源期刊: 工程与科学中的计算机建模(英文)
• 学科: 数学
• 关键词: DEEP learning CNN ACTIVATION function FLUID DYNAMICS MNIST CIFAR-10 CIFAR-100.
• 年，卷（期）: 2019,（1）
• 页码范围: 1-14
• 页数: 14页
• 分类号: O17

摘要

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.