arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2007.11976cs.ARcs.CV
收藏

VLSI实现中双曲正切函数多项式逼近与有理逼近的比较分析

Comparative Analysis of Polynomial and Rational Approximations of Hyperbolic Tangent Function for VLSI Implementation

NXP Semiconductors(恩智浦半导体)

Mahesh Chandra

摘要:

深度神经网络在许多计算机视觉和人机界面应用中产生了最先进的结果,例如目标检测,语音识别等。由于这些网络在计算上是昂贵的,因此定制的加速器被设计用于以较低的成本和功耗实现所需的性能。这些神经网络的关键构建块之一是非线性激活函数,例如sigmoid、双曲正切(tanh)和ReLU。需要激活函数的低复杂度精确硬件实现以满足神经网络加速器的性能和面积目标。尽管已经发表了各种tanh激活函数的方法和实现,但是缺少比较研究。本文对多项式法和有理法进行了比较分析,并给出了它们的硬件实现。

英文摘要:

Deep neural networks yield the state-of-the-art results in many computer vision and human machine interface applications such as object detection, speech recognition etc. Since, these networks are computationally expensive, customized accelerators are designed for achieving the required performance at lower cost and power. One of the key building blocks of these neural networks is non-linear activation function such as sigmoid, hyperbolic tangent (tanh), and ReLU. A low complexity accurate hardware implementation of the activation function is required to meet the performance and area targets of the neural network accelerators. Even though, various methods and implementations of tanh activation function have been published, a comparative study is missing. This paper presents comparative analysis of polynomial and rational methods and their hardware implementation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑