Rectified Exponential Units for Convolutional Neural Networks

Abstract

Rectified linear unit (ReLU) plays an important role in today’s convolutional neural networks (CNNs). In this paper, we propose a novel activation function called Rectified Exponential Unit (REU). Inspired by two recently proposed activation functions: Exponential Linear Unit (ELU) and Swish, the REU is designed by introducing the advantage of flexible exponent and multiplication function form. Moreover, we propose the Parametric REU (PREU) to increase the expressive power of the REU. The experiments with three classical CNN architectures, LeNet-5, Network in Network, and Residual Network (ResNet) on scale-various benchmarks including Fashion-MNIST, CIFAR10, CIFAR100, and Tiny ImageNet demonstrate that REU and PREU achieve improvement compared with other activation functions. Our results show that our REU has relative error improvements over ReLU of 7.74% and 6.08% on CIFAR-10 and 100 with the ResNet, the improvements of PREU is 9.24% and 9.32%. Finally, we use the different PREU variants in the Residual unit to achieve more stable results.

Keywords

• Activation function
• convolutional neural network
• rectified exponential unit
• parametric rectified exponential unit