Hardware-Friendly Approximation for Swish Activation and Its Implementation

Kangjoon Choi,Sungho Kim, Jeongmin Kim,In-Cheol Park

IEEE Transactions on Circuits and Systems II: Express Briefs(2024)

引用 0|浏览1
暂无评分
摘要
This paper addresses the challenges associated with implementing the Swish activation function in hardware. While Swish exhibits improved training performance over the ReLU activation function, its computational complexity poses difficulties in hardware implementation. To mitigate the drawback, an approximation called h-swish was introduced to reduce the computational complexity; however, there were still rooms for improvement. This paper proposes a novel hardware-friendly approximation of Swish and its implementation, which demonstrates significant improvements over h-swish in terms of delay, area, and power consumption.
更多
查看译文
关键词
function approximation,Swish activation,hardware-efficient accelerator,activation function,deep learning
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要