Using recurrent neural networks for circuit complexity modeling

Azam Beg; P. W.Chandana Prasad; Mirza M. Arshad; Khursheed Hasnain

doi:10.1109/INMIC.2006.358161

Using recurrent neural networks for circuit complexity modeling

Azam Beg, P. W.Chandana Prasad, Mirza M. Arshad, Khursheed Hasnain

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

7 Citations (Scopus)

Abstract

Being able to model the complexity of Boolean functions in terms of number of nodes in a Binary Decision Diagram can be quite useful in VLSI/CAD applications. Our investigation showed that it is possible to use the recurrent neural network (RNN) models for the prediction of circuit complexity. The modeling results matched closely with simulations with an average error of less than 1%. The correlation coefficient between RNN's predictions and actual results for ISCAS benchmark circuits was 0.629.

Original language	English
Title of host publication	10th IEEE International Multitopic Conference 2006, INMIC
Pages	194-197
Number of pages	4
DOIs	https://doi.org/10.1109/INMIC.2006.358161
Publication status	Published - 2006
Event	10th IEEE International Multitopic Conference 2006, INMIC - Islamabad, Pakistan Duration: Dec 23 2006 → Dec 24 2006

Publication series

Name	10th IEEE International Multitopic Conference 2006, INMIC

Other

Other	10th IEEE International Multitopic Conference 2006, INMIC
Country/Territory	Pakistan
City	Islamabad
Period	12/23/06 → 12/24/06

ASJC Scopus subject areas

Computer Science(all)
Control and Systems Engineering

Access to Document

10.1109/INMIC.2006.358161

Cite this

Beg, A, Prasad, PWC, Arshad, MM & Hasnain, K 2006, Using recurrent neural networks for circuit complexity modeling. in 10th IEEE International Multitopic Conference 2006, INMIC., 4196404, 10th IEEE International Multitopic Conference 2006, INMIC, pp. 194-197, 10th IEEE International Multitopic Conference 2006, INMIC, Islamabad, Pakistan, 12/23/06. https://doi.org/10.1109/INMIC.2006.358161

@inproceedings{3cec0853ac7b4a0ab421bb5a56592c34,

title = "Using recurrent neural networks for circuit complexity modeling",

abstract = "Being able to model the complexity of Boolean functions in terms of number of nodes in a Binary Decision Diagram can be quite useful in VLSI/CAD applications. Our investigation showed that it is possible to use the recurrent neural network (RNN) models for the prediction of circuit complexity. The modeling results matched closely with simulations with an average error of less than 1%. The correlation coefficient between RNN's predictions and actual results for ISCAS benchmark circuits was 0.629.",

author = "Azam Beg and Prasad, {P. W.Chandana} and Arshad, {Mirza M.} and Khursheed Hasnain",

year = "2006",

doi = "10.1109/INMIC.2006.358161",

language = "English",

isbn = "142440794X",

series = "10th IEEE International Multitopic Conference 2006, INMIC",

pages = "194--197",

booktitle = "10th IEEE International Multitopic Conference 2006, INMIC",

note = "10th IEEE International Multitopic Conference 2006, INMIC ; Conference date: 23-12-2006 Through 24-12-2006",

}

TY - GEN

T1 - Using recurrent neural networks for circuit complexity modeling

AU - Beg, Azam

AU - Prasad, P. W.Chandana

AU - Arshad, Mirza M.

AU - Hasnain, Khursheed

PY - 2006

Y1 - 2006

N2 - Being able to model the complexity of Boolean functions in terms of number of nodes in a Binary Decision Diagram can be quite useful in VLSI/CAD applications. Our investigation showed that it is possible to use the recurrent neural network (RNN) models for the prediction of circuit complexity. The modeling results matched closely with simulations with an average error of less than 1%. The correlation coefficient between RNN's predictions and actual results for ISCAS benchmark circuits was 0.629.

AB - Being able to model the complexity of Boolean functions in terms of number of nodes in a Binary Decision Diagram can be quite useful in VLSI/CAD applications. Our investigation showed that it is possible to use the recurrent neural network (RNN) models for the prediction of circuit complexity. The modeling results matched closely with simulations with an average error of less than 1%. The correlation coefficient between RNN's predictions and actual results for ISCAS benchmark circuits was 0.629.

UR - http://www.scopus.com/inward/record.url?scp=46449085032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=46449085032&partnerID=8YFLogxK

U2 - 10.1109/INMIC.2006.358161

DO - 10.1109/INMIC.2006.358161

M3 - Conference contribution

AN - SCOPUS:46449085032

SN - 142440794X

SN - 9781424407941

T3 - 10th IEEE International Multitopic Conference 2006, INMIC

SP - 194

EP - 197

BT - 10th IEEE International Multitopic Conference 2006, INMIC

T2 - 10th IEEE International Multitopic Conference 2006, INMIC

Y2 - 23 December 2006 through 24 December 2006

ER -

Using recurrent neural networks for circuit complexity modeling

Abstract

Publication series

Other

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this