返回
Trainable activation function with differentiable negative side and adaptable rectified point
DOI:10.1007/s10489-020-01885-z.png)
摘要
En 中文
Activation function is one of the keys for Artificial Neural Network in learning complex mapping function. A recently proposed activation function called Scaled Exponential Linear Unit (SELU) has a unique characteristic in the ability to automatically normalize its output toward predefined mean and variance. In this paper, we introduce Parametric Scaled Exponential Linear Unit (PSELU), a modification of SELU where the parameters are adaptively learned during the training phase via backpropagation algorithm. We then add further modifications with the aim of having a stronger gradient in the negative part and produce more negative output from our proposed method. Our proposed method is evaluated using various artificial neural network models on diverse image classification tasks. In addition, we also measure the performance of our proposed method in comparison with some other popular activation functions. The evaluation results in this paper present some empirical proof of improvement in term of network generalization performance. Moreover, our experiments strengthen our initial hypothesis regarding the advantages obtained from using our proposed method. Finally, the behavior of the trained parameters along with the training phase dynamic is observed in order to better understand the increased performance of our proposed method
Keyword:
Activation functions
Self-normalizing neural networks
Parameterized learning
Rectified point
AI总结
对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
3.5
论文数:
7.6K
被引数:
1.7W
机构
引用论文
Os benefícios da aplicação de iterações para avaliação de funções e para definição de soluções de design e engenharia no processo de desenvolvimento integrado de produtos迭代在产品集成开发过程中用于评估函数、定义设计及工程解决方案的益处。
Do Perceptions of Competence Mediate The Relationship Between Fundamental Motor Skill Proficiency and Physical Activity Levels of Children in Kindergarten?能力的感知是否可以介导幼儿园儿童的基本运动技能熟练程度与身体活动水平之间的关系?
Structural study of lanthanides(III) in aqueous nitrate and chloride solutions by EXAFS通过EXAFS对硝酸盐和氯化物水溶液中镧系元素 (III) 的结构研究
Gradient-based learning applied to document recognition基于梯度的学习在文档识别中的应用
PROCEEDINGS OF THE IEEE
IF25.9

