Computing hyperbolic tangent and sigmoid functions using stochastic logic

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

This paper addresses implementations of tangent hyperbolic and sigmoid functions using stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Tangent hyperbolic and sigmoid functions are widely used in machine learning systems such as neural networks. This paper makes two major contributions. First, two approaches are proposed to implementing tangent hyperbolic and sigmoid functions in unipolar stochastic logic. The first approach is based on a JK flip-flop. In the second approach, the proposed designs are based on a general unipolar division. Second, we present two approaches to computing tangent hyperbolic and sigmoid functions in bipolar stochastic logic. The first approach involves format conversion from bipolar format to unipolar format. The second approach uses a general bipolar stochastic divider. Simulation and synthesis results are presented for proposed designs.

Original languageEnglish (US)
Title of host publicationConference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
EditorsMichael B. Matthews
PublisherIEEE Computer Society
Pages1580-1585
Number of pages6
ISBN (Electronic)9781538639542
DOIs
StatePublished - Mar 1 2017
Event50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 - Pacific Grove, United States
Duration: Nov 6 2016Nov 9 2016

Publication series

NameConference Record - Asilomar Conference on Signals, Systems and Computers
ISSN (Print)1058-6393

Other

Other50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016
CountryUnited States
CityPacific Grove
Period11/6/1611/9/16

Fingerprint

Learning systems
Logic gates
Flip flop circuits
Neural networks

Keywords

  • Bipolar format
  • Sigmoid function
  • Stochastic division
  • Stochastic logic
  • Tangent hyperbolic
  • Unipolar format

Cite this

Liu, Y., & Parhi, K. K. (2017). Computing hyperbolic tangent and sigmoid functions using stochastic logic. In M. B. Matthews (Ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016 (pp. 1580-1585). [7869645] (Conference Record - Asilomar Conference on Signals, Systems and Computers). IEEE Computer Society. https://doi.org/10.1109/ACSSC.2016.7869645

Computing hyperbolic tangent and sigmoid functions using stochastic logic. / Liu, Yin; Parhi, Keshab K.

Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. ed. / Michael B. Matthews. IEEE Computer Society, 2017. p. 1580-1585 7869645 (Conference Record - Asilomar Conference on Signals, Systems and Computers).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liu, Y & Parhi, KK 2017, Computing hyperbolic tangent and sigmoid functions using stochastic logic. in MB Matthews (ed.), Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016., 7869645, Conference Record - Asilomar Conference on Signals, Systems and Computers, IEEE Computer Society, pp. 1580-1585, 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016, Pacific Grove, United States, 11/6/16. https://doi.org/10.1109/ACSSC.2016.7869645
Liu Y, Parhi KK. Computing hyperbolic tangent and sigmoid functions using stochastic logic. In Matthews MB, editor, Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. IEEE Computer Society. 2017. p. 1580-1585. 7869645. (Conference Record - Asilomar Conference on Signals, Systems and Computers). https://doi.org/10.1109/ACSSC.2016.7869645
Liu, Yin ; Parhi, Keshab K. / Computing hyperbolic tangent and sigmoid functions using stochastic logic. Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016. editor / Michael B. Matthews. IEEE Computer Society, 2017. pp. 1580-1585 (Conference Record - Asilomar Conference on Signals, Systems and Computers).
@inproceedings{c4f2e312c86c44729badf25cce7e724a,
title = "Computing hyperbolic tangent and sigmoid functions using stochastic logic",
abstract = "This paper addresses implementations of tangent hyperbolic and sigmoid functions using stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Tangent hyperbolic and sigmoid functions are widely used in machine learning systems such as neural networks. This paper makes two major contributions. First, two approaches are proposed to implementing tangent hyperbolic and sigmoid functions in unipolar stochastic logic. The first approach is based on a JK flip-flop. In the second approach, the proposed designs are based on a general unipolar division. Second, we present two approaches to computing tangent hyperbolic and sigmoid functions in bipolar stochastic logic. The first approach involves format conversion from bipolar format to unipolar format. The second approach uses a general bipolar stochastic divider. Simulation and synthesis results are presented for proposed designs.",
keywords = "Bipolar format, Sigmoid function, Stochastic division, Stochastic logic, Tangent hyperbolic, Unipolar format",
author = "Yin Liu and Parhi, {Keshab K.}",
year = "2017",
month = "3",
day = "1",
doi = "10.1109/ACSSC.2016.7869645",
language = "English (US)",
series = "Conference Record - Asilomar Conference on Signals, Systems and Computers",
publisher = "IEEE Computer Society",
pages = "1580--1585",
editor = "Matthews, {Michael B.}",
booktitle = "Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016",

}

TY - GEN

T1 - Computing hyperbolic tangent and sigmoid functions using stochastic logic

AU - Liu, Yin

AU - Parhi, Keshab K.

PY - 2017/3/1

Y1 - 2017/3/1

N2 - This paper addresses implementations of tangent hyperbolic and sigmoid functions using stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Tangent hyperbolic and sigmoid functions are widely used in machine learning systems such as neural networks. This paper makes two major contributions. First, two approaches are proposed to implementing tangent hyperbolic and sigmoid functions in unipolar stochastic logic. The first approach is based on a JK flip-flop. In the second approach, the proposed designs are based on a general unipolar division. Second, we present two approaches to computing tangent hyperbolic and sigmoid functions in bipolar stochastic logic. The first approach involves format conversion from bipolar format to unipolar format. The second approach uses a general bipolar stochastic divider. Simulation and synthesis results are presented for proposed designs.

AB - This paper addresses implementations of tangent hyperbolic and sigmoid functions using stochastic logic. Stochastic computing requires simple logic gates and is inherently fault-tolerant. Thus, these structures are well suited for nanoscale CMOS technologies. Tangent hyperbolic and sigmoid functions are widely used in machine learning systems such as neural networks. This paper makes two major contributions. First, two approaches are proposed to implementing tangent hyperbolic and sigmoid functions in unipolar stochastic logic. The first approach is based on a JK flip-flop. In the second approach, the proposed designs are based on a general unipolar division. Second, we present two approaches to computing tangent hyperbolic and sigmoid functions in bipolar stochastic logic. The first approach involves format conversion from bipolar format to unipolar format. The second approach uses a general bipolar stochastic divider. Simulation and synthesis results are presented for proposed designs.

KW - Bipolar format

KW - Sigmoid function

KW - Stochastic division

KW - Stochastic logic

KW - Tangent hyperbolic

KW - Unipolar format

UR - http://www.scopus.com/inward/record.url?scp=85016331645&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016331645&partnerID=8YFLogxK

U2 - 10.1109/ACSSC.2016.7869645

DO - 10.1109/ACSSC.2016.7869645

M3 - Conference contribution

AN - SCOPUS:85016331645

T3 - Conference Record - Asilomar Conference on Signals, Systems and Computers

SP - 1580

EP - 1585

BT - Conference Record of the 50th Asilomar Conference on Signals, Systems and Computers, ACSSC 2016

A2 - Matthews, Michael B.

PB - IEEE Computer Society

ER -