A Hardware-Efficient Sigmoid Function With Adjustable Precision for a Neural Network System

檔案

本條目沒有附加檔案。

至出版者網站查看(DOI) ›

日期

2015-11-01

類型

期刊名稱

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS

卷期與頁次

第 62 卷第 11 期,頁 1073–1077

ISSN

1549-7747

語言

英文

摘要

A hardware-efficient sigmoid function calculator with adjustable precision for neural network and deep-learning applications is proposed in this brief. By adopting the bit-plane format of the input and output values, the computational latency of the processing time can be dynamically reduced according to the user configuration. To reduce the hardware cost, the coefficients used to calculate the sigmoid value can be shared for multiple calculators without any structural hazard. In addition, the restricted constraint is applied in the coefficients\' training stage to further simplify the computation in the calculation stage with a negligible quality loss. A test module is designed for the proposal and operated at 300 MHz to achieve 75 million sigmoid calculations per second. Implemented in 90-nm CMOS technology, the core of the calculator costs 1663 gates, and a 1-kb globally shared memory is used to store the coefficients.

所屬典藏

期刊論文
顯示完整詮釋資料 統計資料

引用此條目

Tsai, C.-H., Chih, Y.-T., Wong, W. H., & Lee, C.-Y. (2015). A Hardware-Efficient Sigmoid Function With Adjustable Precision for a Neural Network System. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS, 62(11), 1073–1077. https://doi.org/10.1109/TCSII.2015.2456531

BibTeX RIS

引用文字依 APA 第 7 版格式自動產生,使用前請再核對。

分享

永久網址:https://ir.lib.nycu.edu.tw/handle/11536/129390