【作者单位】School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China School of Information Science and Technology, Tibet University, Lhasa, China School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China
【年份】2020
【卷号】Vol.8
【页码】72727-72741
【ISSN】2169-3536
【关键词】Biological neural networks Training Neurons Machine learning Task analysis Optimization Activation function deep learning memristive window function muilti-layer perceptron RMAF
【摘要】 Activation functions facilitate deep neural networks by introducing non-linearity to the learning process. The non-linearity feature gives the neural network the ability to learn complex patterns. Recently, the most widely used activation function is...