A serial complexity measure of neural networks

Moshe Sipper

doi:10.1109/ICNN.1993.298687

A serial complexity measure of neural networks

Moshe Sipper

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

30 Scopus citations

Abstract

The most common methodology of neural network analysis is that of simulation since as of yet there is no common formal framework. Towards this end we adopt one measure of serial algorithms, namely that of serial computational complexity and apply it to the analysis of neural networks. We analyze various networks and derive their complexity, thus providing insight as to their computational requirements.

Original language	English
Title of host publication	1993 IEEE International Conference on Neural Networks, ICNN 1993
Publisher	Institute of Electrical and Electronics Engineers
Pages	962-966
Number of pages	5
ISBN (Electronic)	0780309995
DOIs	https://doi.org/10.1109/ICNN.1993.298687
State	Published - 1 Jan 1993
Externally published	Yes
Event	IEEE International Conference on Neural Networks, ICNN 1993 - San Francisco, United States Duration: 28 Mar 1993 → 1 Apr 1993

Publication series

Name	IEEE International Conference on Neural Networks - Conference Proceedings
Volume	1993-January
ISSN (Print)	2161-4393

Conference

Conference	IEEE International Conference on Neural Networks, ICNN 1993
Country/Territory	United States
City	San Francisco
Period	28/03/93 → 1/04/93

ASJC Scopus subject areas

Software

Access to Document

10.1109/ICNN.1993.298687

Cite this

@inproceedings{dbc21710697c42389feb254e85df1344,

title = "A serial complexity measure of neural networks",

abstract = "The most common methodology of neural network analysis is that of simulation since as of yet there is no common formal framework. Towards this end we adopt one measure of serial algorithms, namely that of serial computational complexity and apply it to the analysis of neural networks. We analyze various networks and derive their complexity, thus providing insight as to their computational requirements.",

author = "Moshe Sipper",

note = "Publisher Copyright: {\textcopyright} 1993 IEEE.; IEEE International Conference on Neural Networks, ICNN 1993 ; Conference date: 28-03-1993 Through 01-04-1993",

year = "1993",

month = jan,

day = "1",

doi = "10.1109/ICNN.1993.298687",

language = "English",

series = "IEEE International Conference on Neural Networks - Conference Proceedings",

publisher = "Institute of Electrical and Electronics Engineers",

pages = "962--966",

booktitle = "1993 IEEE International Conference on Neural Networks, ICNN 1993",

address = "United States",

}

Sipper, M 1993, A serial complexity measure of neural networks. in 1993 IEEE International Conference on Neural Networks, ICNN 1993., 298687, IEEE International Conference on Neural Networks - Conference Proceedings, vol. 1993-January, Institute of Electrical and Electronics Engineers, pp. 962-966, IEEE International Conference on Neural Networks, ICNN 1993, San Francisco, United States, 28/03/93. https://doi.org/10.1109/ICNN.1993.298687

A serial complexity measure of neural networks. / Sipper, Moshe.
1993 IEEE International Conference on Neural Networks, ICNN 1993. Institute of Electrical and Electronics Engineers, 1993. p. 962-966 298687 (IEEE International Conference on Neural Networks - Conference Proceedings; Vol. 1993-January).

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

TY - GEN

T1 - A serial complexity measure of neural networks

AU - Sipper, Moshe

PY - 1993/1/1

Y1 - 1993/1/1

N2 - The most common methodology of neural network analysis is that of simulation since as of yet there is no common formal framework. Towards this end we adopt one measure of serial algorithms, namely that of serial computational complexity and apply it to the analysis of neural networks. We analyze various networks and derive their complexity, thus providing insight as to their computational requirements.

AB - The most common methodology of neural network analysis is that of simulation since as of yet there is no common formal framework. Towards this end we adopt one measure of serial algorithms, namely that of serial computational complexity and apply it to the analysis of neural networks. We analyze various networks and derive their complexity, thus providing insight as to their computational requirements.

UR - http://www.scopus.com/inward/record.url?scp=84943303348&partnerID=8YFLogxK

U2 - 10.1109/ICNN.1993.298687

DO - 10.1109/ICNN.1993.298687

M3 - Conference contribution

AN - SCOPUS:84943303348

T3 - IEEE International Conference on Neural Networks - Conference Proceedings

SP - 962

EP - 966

BT - 1993 IEEE International Conference on Neural Networks, ICNN 1993

PB - Institute of Electrical and Electronics Engineers

T2 - IEEE International Conference on Neural Networks, ICNN 1993

Y2 - 28 March 1993 through 1 April 1993

ER -

A serial complexity measure of neural networks

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this