• Complex
  • Title
  • Keyword
  • Abstract
  • Scholars
  • Journal
  • ISSN
  • Conference
搜索

Author:

Jiang, Nan (Jiang, Nan.) | Hou, Ligang (Hou, Ligang.) | Guo, Jia (Guo, Jia.) | Zhang, Xinyi (Zhang, Xinyi.) | Lv, Ang (Lv, Ang.)

Indexed by:

CPCI-S

Abstract:

One of the difficulties encountered in realizing artificial neural network based on VLSI is the choice of the implementation method of activation function. At present, the main approaches to solve this problem are piecewise nonlinear approximation and bit level mapping. Based on hyperbolic tangent, the final output error of the two methods is discussed through the hardware implementation and software analysis of the artificial neural network nodes. We found that the nonlinear approximation method has the problem of large output fluctuation, and the amplification effect of the backpropagation can not be ignored. Therefore, this paper proposes that the bit level mapping method has more advantages in practical applications in the implementation of high-precision artificial neural nodes.

Keyword:

artificial neural network VLSI piecewise nonlinear approximation bit level mapping

Author Community:

  • [ 1 ] [Jiang, Nan]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China
  • [ 2 ] [Hou, Ligang]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China
  • [ 3 ] [Guo, Jia]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China
  • [ 4 ] [Zhang, Xinyi]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China
  • [ 5 ] [Lv, Ang]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China

Reprint Author's Address:

  • [Hou, Ligang]Beijing Univ Technol, VLSI & Syst Lab, Beijing, Peoples R China

Show more details

Related Keywords:

Related Article:

Source :

2018 3RD IEEE INTERNATIONAL CONFERENCE ON INTEGRATED CIRCUITS AND MICROSYSTEMS (ICICM)

Year: 2018

Page: 278-281

Language: English

Cited Count:

WoS CC Cited Count: 6

SCOPUS Cited Count:

ESI Highly Cited Papers on the List: 0 Unfold All

WanFang Cited Count:

Chinese Cited Count:

30 Days PV: 4

Affiliated Colleges:

Online/Total:704/5455642
Address:BJUT Library(100 Pingleyuan,Chaoyang District,Beijing 100124, China Post Code:100124) Contact Us:010-67392185
Copyright:BJUT Library Technical Support:Beijing Aegean Software Co., Ltd.