arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.02078cs.AReess.SP
收藏

一种新的双曲正切函数的可扩展VLSI实现方法

A Novel Method for Scalable VLSI Implementation of Hyperbolic Tangent Function

Mahesh Chandra

摘要:

双曲正切函数和Sigmoid函数被用作人工神经网络和深度神经网络中的非线性激活单元。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率实现所需的性能。激活函数和MAC单元是这些神经网络的关键构建块。需要激活函数的低复杂度和精确的硬件实现来满足这种神经网络加速器的性能和面积目标。此外,需要可扩展的实现,因为最近的研究表明,DNN可能在不同的层中使用不同的精度。提出了一种基于双曲函数三角展开性质的硬件实现方法,该方法可以根据不同的精度和精度要求进行调整。

英文摘要:

Hyperbolic tangent and Sigmoid functions are used as non-linear activation units in the artificial and deep neural networks. Since, these networks are computationally expensive, customized accelerators are designed for achieving the required performance at lower cost and power. The activation function and MAC units are the key building blocks of these neural networks. A low complexity and accurate hardware implementation of the activation function is required to meet the performance and area targets of such neural network accelerators. Moreover, a scalable implementation is required as the recent studies show that the DNNs may use different precision in different layers. This paper presents a novel method based on trigonometric expansion properties of the hyperbolic function for hardware implementation which can be easily tuned for different accuracy and precision requirements.

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。

↑