Comparing digital neural network architectures

Yaron Kashai; Yair Be'ery

doi:10.1109/EEIS.1991.217663

Comparing digital neural network architectures

Yaron Kashai, Yair Be'ery

School of Electrical Engineering

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

Abstract

A method of assessing the quality of digital neural networks is proposed. This method, which consists of calculating a few measures, provides indications for network qualities, without specifying the processing elements. This feature makes the proposed method applicable to a variety of architectures. The method is demonstrated for three different architectures. The insight gained by measuring them suggested several improvements, whose contributions are predicted by the method.

Original language	English
Title of host publication	Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	203-206
Number of pages	4
ISBN (Electronic)	0879426780, 9780879426781
DOIs	https://doi.org/10.1109/EEIS.1991.217663
State	Published - 1991
Event	17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991 - Tel Aviv, Israel Duration: 5 Mar 1991 → 7 Mar 1991

Publication series

Name	Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

Conference

Conference	17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991
Country/Territory	Israel
City	Tel Aviv
Period	5/03/91 → 7/03/91

Access to Document

10.1109/EEIS.1991.217663

Cite this

Kashai, Y., & Be'ery, Y. (1991). Comparing digital neural network architectures. In Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991 (pp. 203-206). [217663] (Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EEIS.1991.217663

@inproceedings{6ccfc185d8d24fe9982aaf31b2d6effd,

title = "Comparing digital neural network architectures",

abstract = "A method of assessing the quality of digital neural networks is proposed. This method, which consists of calculating a few measures, provides indications for network qualities, without specifying the processing elements. This feature makes the proposed method applicable to a variety of architectures. The method is demonstrated for three different architectures. The insight gained by measuring them suggested several improvements, whose contributions are predicted by the method.",

author = "Yaron Kashai and Yair Be'ery",

note = "Publisher Copyright: {\textcopyright} Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991. All rights reserved.; 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991 ; Conference date: 05-03-1991 Through 07-03-1991",

year = "1991",

doi = "10.1109/EEIS.1991.217663",

language = "אנגלית",

series = "Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991",

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

pages = "203--206",

booktitle = "Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991",

address = "ארצות הברית",

}

Kashai, Y & Be'ery, Y 1991, Comparing digital neural network architectures. in Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991., 217663, Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991, Institute of Electrical and Electronics Engineers Inc., pp. 203-206, 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991, Tel Aviv, Israel, 5/03/91. https://doi.org/10.1109/EEIS.1991.217663

Comparing digital neural network architectures. / Kashai, Yaron; Be'ery, Yair.
Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991. Institute of Electrical and Electronics Engineers Inc., 1991. p. 203-206 217663 (Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991).

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

TY - GEN

T1 - Comparing digital neural network architectures

AU - Kashai, Yaron

AU - Be'ery, Yair

PY - 1991

Y1 - 1991

N2 - A method of assessing the quality of digital neural networks is proposed. This method, which consists of calculating a few measures, provides indications for network qualities, without specifying the processing elements. This feature makes the proposed method applicable to a variety of architectures. The method is demonstrated for three different architectures. The insight gained by measuring them suggested several improvements, whose contributions are predicted by the method.

AB - A method of assessing the quality of digital neural networks is proposed. This method, which consists of calculating a few measures, provides indications for network qualities, without specifying the processing elements. This feature makes the proposed method applicable to a variety of architectures. The method is demonstrated for three different architectures. The insight gained by measuring them suggested several improvements, whose contributions are predicted by the method.

UR - http://www.scopus.com/inward/record.url?scp=85067604524&partnerID=8YFLogxK

U2 - 10.1109/EEIS.1991.217663

DO - 10.1109/EEIS.1991.217663

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85067604524

T3 - Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

SP - 203

EP - 206

BT - Proceedings - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 17th Convention of Electrical and Electronics Engineers in Israel, EEIS 1991

Y2 - 5 March 1991 through 7 March 1991

ER -

Comparing digital neural network architectures

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this