Design of An Analog Circuit-Based Artificial Neural Network

Fikret Basar Gencer; Xhesila Xhafa; Benan Beril Inam; Mustafa Berke Yelten

doi:10.23919/ELECO47770.2019.8990559

Design of An Analog Circuit-Based Artificial Neural Network

Fikret Basar Gencer, Xhesila Xhafa, Benan Beril Inam, Mustafa Berke Yelten

Department of Electronics and Communication Engineering

Istanbul Technical University

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

2 Citations (Scopus)

Abstract

In this paper, a feed-forward artificial neural network with a single hidden layer has been realized using analog circuit blocks designed in 90 nm UMC technology. The network is capable of solving non-linearly separable problems and successfully realizes the XOR gate, which is one of the most basic and common non-linear classification problems. The inputs and the weights of the network are represented by the amplitudes of the transient signals. The weights have been calculated through the back-propagation (BP) algorithm. The analog circuit-based learning implementation yields accurate results with the expected outputs.

Original language	English
Title of host publication	ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	379-383
Number of pages	5
ISBN (Electronic)	9786050112757
DOIs	https://doi.org/10.23919/ELECO47770.2019.8990559
Publication status	Published - Nov 2019
Event	11th International Conference on Electrical and Electronics Engineering, ELECO 2019 - Bursa, Turkey Duration: 28 Nov 2019 → 30 Nov 2019

Publication series

Name	ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering

Conference

Conference	11th International Conference on Electrical and Electronics Engineering, ELECO 2019
Country/Territory	Turkey
City	Bursa
Period	28/11/19 → 30/11/19

Bibliographical note

Publisher Copyright:
© 2019 Chamber of Turkish Electrical Engineers.

Access to Document

10.23919/ELECO47770.2019.8990559

Cite this

Gencer, F. B., Xhafa, X., Inam, B. B., & Berke Yelten, M. (2019). Design of An Analog Circuit-Based Artificial Neural Network. In ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering (pp. 379-383). Article 8990559 (ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ELECO47770.2019.8990559

Gencer, Fikret Basar ; Xhafa, Xhesila ; Inam, Benan Beril et al. / Design of An Analog Circuit-Based Artificial Neural Network. ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 379-383 (ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering).

@inproceedings{e9ae7d8380164436b49f6fb6da104874,

title = "Design of An Analog Circuit-Based Artificial Neural Network",

abstract = "In this paper, a feed-forward artificial neural network with a single hidden layer has been realized using analog circuit blocks designed in 90 nm UMC technology. The network is capable of solving non-linearly separable problems and successfully realizes the XOR gate, which is one of the most basic and common non-linear classification problems. The inputs and the weights of the network are represented by the amplitudes of the transient signals. The weights have been calculated through the back-propagation (BP) algorithm. The analog circuit-based learning implementation yields accurate results with the expected outputs.",

author = "Gencer, \{Fikret Basar\} and Xhesila Xhafa and Inam, \{Benan Beril\} and \{Berke Yelten\}, Mustafa",

note = "Publisher Copyright: {\textcopyright} 2019 Chamber of Turkish Electrical Engineers.; 11th International Conference on Electrical and Electronics Engineering, ELECO 2019 ; Conference date: 28-11-2019 Through 30-11-2019",

year = "2019",

month = nov,

doi = "10.23919/ELECO47770.2019.8990559",

language = "English",

series = "ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

pages = "379--383",

booktitle = "ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering",

address = "United States",

}

Gencer, FB, Xhafa, X, Inam, BB & Berke Yelten, M 2019, Design of An Analog Circuit-Based Artificial Neural Network. in ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering., 8990559, ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering, Institute of Electrical and Electronics Engineers Inc., pp. 379-383, 11th International Conference on Electrical and Electronics Engineering, ELECO 2019, Bursa, Turkey, 28/11/19. https://doi.org/10.23919/ELECO47770.2019.8990559

Design of An Analog Circuit-Based Artificial Neural Network. / Gencer, Fikret Basar; Xhafa, Xhesila; Inam, Benan Beril et al.
ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering. Institute of Electrical and Electronics Engineers Inc., 2019. p. 379-383 8990559 (ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Design of An Analog Circuit-Based Artificial Neural Network

AU - Gencer, Fikret Basar

AU - Xhafa, Xhesila

AU - Inam, Benan Beril

AU - Berke Yelten, Mustafa

PY - 2019/11

Y1 - 2019/11

N2 - In this paper, a feed-forward artificial neural network with a single hidden layer has been realized using analog circuit blocks designed in 90 nm UMC technology. The network is capable of solving non-linearly separable problems and successfully realizes the XOR gate, which is one of the most basic and common non-linear classification problems. The inputs and the weights of the network are represented by the amplitudes of the transient signals. The weights have been calculated through the back-propagation (BP) algorithm. The analog circuit-based learning implementation yields accurate results with the expected outputs.

AB - In this paper, a feed-forward artificial neural network with a single hidden layer has been realized using analog circuit blocks designed in 90 nm UMC technology. The network is capable of solving non-linearly separable problems and successfully realizes the XOR gate, which is one of the most basic and common non-linear classification problems. The inputs and the weights of the network are represented by the amplitudes of the transient signals. The weights have been calculated through the back-propagation (BP) algorithm. The analog circuit-based learning implementation yields accurate results with the expected outputs.

UR - https://www.scopus.com/pages/publications/85080931120

U2 - 10.23919/ELECO47770.2019.8990559

DO - 10.23919/ELECO47770.2019.8990559

M3 - Conference contribution

AN - SCOPUS:85080931120

T3 - ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering

SP - 379

EP - 383

BT - ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 11th International Conference on Electrical and Electronics Engineering, ELECO 2019

Y2 - 28 November 2019 through 30 November 2019

ER -

Gencer FB, Xhafa X, Inam BB, Berke Yelten M. Design of An Analog Circuit-Based Artificial Neural Network. In ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering. Institute of Electrical and Electronics Engineers Inc. 2019. p. 379-383. 8990559. (ELECO 2019 - 11th International Conference on Electrical and Electronics Engineering). doi: 10.23919/ELECO47770.2019.8990559

Design of An Analog Circuit-Based Artificial Neural Network

Abstract

Publication series

Conference

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this