.png){kind=icon}
返回
A Dynamic Rectified Linear Activation Units
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2019.2959036.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural network regression models produce substantial gains in big data prediction systems. Multilayer perceptron neural (MPL) networks have more various properties than single-layer feedforward neural networks. A deeper neural network is more intelligent and sophisticated, which is one of the main research directions. However, the disappearing gradient is the primary problem that restricts the research. The appropriate activation function is one of the effective methods for solving this problem. A bold idea about activation functions emerged: if the activation function is different in two adjacent training epochs, the probability of the same gradient value will be small. We proposed a novel activation function whose shape can be changed dynamically in training. Our experimental results show that this activation function with dynamic characteristics can effectively avoid the disappearing gradient and can make the multilayer perceptron neural networks deeper.
Keyword:
Deep neural networks
convergent dynamic activation function
vanishing gradient
non-additional calculation
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:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
分享收藏Real-time and offline techniques for identifying obstructive sleep apnea patients用于识别阻塞性睡眠呼吸暂停患者的实时和离线技术
PREAI
分享收藏Improved Convolutional Neural Network Based on Fast Exponentially Linear Unit Activation Function.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAI分享收藏
查看更多内容