A methodology for evaluation time approximation

P. W.C. Prasad; Azam Beg

doi:10.1109/MWSCAS.2007.4488692

A methodology for evaluation time approximation

P. W.C. Prasad, Azam Beg

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

5 Citations (Scopus)

Abstract

This paper describes a feed-forward neural network model (FFNNM) for complexity prediction of path related objective functions, mainly average path length (APL) of an arbitrary Boolean function (BF). The proposed model is determined by neural training process of evaluation time derived from the Monte Carlo data of randomly generated BFs. Experimental results show a good correlation between the ISCAS benchmark circuits and those predicted by the FFNNM. This model is capable of providing an estimation of the performance of a circuit prior to its final implementation.

Original language	English
Title of host publication	2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference Proceedings
Pages	776-778
Number of pages	3
DOIs	https://doi.org/10.1109/MWSCAS.2007.4488692
Publication status	Published - 2007
Event	2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference - Montreal, QC, Canada Duration: Aug 5 2007 → Aug 8 2007

Publication series

Name	Midwest Symposium on Circuits and Systems
ISSN (Print)	1548-3746

Other

Other	2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference
Country/Territory	Canada
City	Montreal, QC
Period	8/5/07 → 8/8/07

ASJC Scopus subject areas

Electronic, Optical and Magnetic Materials
Electrical and Electronic Engineering

Access to Document

10.1109/MWSCAS.2007.4488692

Cite this

Prasad, PWC & Beg, A 2007, A methodology for evaluation time approximation. in 2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference Proceedings., 4488692, Midwest Symposium on Circuits and Systems, pp. 776-778, 2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference, Montreal, QC, Canada, 8/5/07. https://doi.org/10.1109/MWSCAS.2007.4488692

@inproceedings{eaf29c59885b4f68bb298aeb781117e6,

title = "A methodology for evaluation time approximation",

abstract = "This paper describes a feed-forward neural network model (FFNNM) for complexity prediction of path related objective functions, mainly average path length (APL) of an arbitrary Boolean function (BF). The proposed model is determined by neural training process of evaluation time derived from the Monte Carlo data of randomly generated BFs. Experimental results show a good correlation between the ISCAS benchmark circuits and those predicted by the FFNNM. This model is capable of providing an estimation of the performance of a circuit prior to its final implementation.",

author = "Prasad, {P. W.C.} and Azam Beg",

year = "2007",

doi = "10.1109/MWSCAS.2007.4488692",

language = "English",

isbn = "1424411769",

series = "Midwest Symposium on Circuits and Systems",

pages = "776--778",

booktitle = "2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference Proceedings",

note = "2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference ; Conference date: 05-08-2007 Through 08-08-2007",

}

TY - GEN

T1 - A methodology for evaluation time approximation

AU - Prasad, P. W.C.

AU - Beg, Azam

PY - 2007

Y1 - 2007

N2 - This paper describes a feed-forward neural network model (FFNNM) for complexity prediction of path related objective functions, mainly average path length (APL) of an arbitrary Boolean function (BF). The proposed model is determined by neural training process of evaluation time derived from the Monte Carlo data of randomly generated BFs. Experimental results show a good correlation between the ISCAS benchmark circuits and those predicted by the FFNNM. This model is capable of providing an estimation of the performance of a circuit prior to its final implementation.

AB - This paper describes a feed-forward neural network model (FFNNM) for complexity prediction of path related objective functions, mainly average path length (APL) of an arbitrary Boolean function (BF). The proposed model is determined by neural training process of evaluation time derived from the Monte Carlo data of randomly generated BFs. Experimental results show a good correlation between the ISCAS benchmark circuits and those predicted by the FFNNM. This model is capable of providing an estimation of the performance of a circuit prior to its final implementation.

UR - http://www.scopus.com/inward/record.url?scp=51449093315&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449093315&partnerID=8YFLogxK

U2 - 10.1109/MWSCAS.2007.4488692

DO - 10.1109/MWSCAS.2007.4488692

M3 - Conference contribution

AN - SCOPUS:51449093315

SN - 1424411769

SN - 9781424411764

T3 - Midwest Symposium on Circuits and Systems

SP - 776

EP - 778

BT - 2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference Proceedings

T2 - 2007 50th Midwest Symposium on Circuits and Systems, MWSCAS - Conference

Y2 - 5 August 2007 through 8 August 2007

ER -

A methodology for evaluation time approximation

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this