Improved Convolutional Neural Network Based on Fast Exponentially Linear Unit Activation Function

• Published in: IEEE access Vol. 7; pp. 151359 - 151367
• Main Authors: Qiumei, Zheng, Dan, Tan, Fenghua, Wang
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Activation function; Artificial neural networks; Biological neural networks; Classification; Convolutional neural networks; deep learning; exponential function; Feature extraction; Mathematical analysis; Mathematical model; Neural networks; Neurons; Noise robustness; Training
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2948112

The activation functions play increasingly important roles in deep convolutional neural networks. The traditional activation functions have some problems such as gradient disappearance, neuron death and output offset, and so on. To solve these problems, we propose a new activation function in this paper, Fast Exponentially Linear Unit (FELU), aiming to speed up exponential linear calculations and reduce the time of network running. FELU has the advantages of Rectified Linear Unit (RELU) and Exponential Linear Unit (ELU), leading to have better classification accuracy and faster calculation speed. We test five traditional activation functions such as ReLU, ELU, SLU, MPELU, TReLU, and our new activation function on the cifar10, cifar100 and GTSRB data sets. Experiments show that the proposed activation function FELU not only improves the speed of the exponential calculation, reducing the time of convolutional neural network running, but also effectively enhances the noise robustness of network to improve the accuracy of classification.