Title :
A methodology for evaluation time approximation
Author :
Prasad, P.W.C. ; Beg, Azam
Author_Institution :
United Arab Emirates Univ., Al-Ain
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.
Keywords :
feedforward neural nets; learning (artificial intelligence); Monte Carlo data; arbitrary Boolean function; average path length; complexity prediction; evaluation time approximation; feed-forward neural network model; neural training process; path related objective function; Binary decision diagrams; Brain modeling; Circuits; Data structures; Educational institutions; Feedforward neural networks; Feedforward systems; Information technology; Neural networks; Predictive models;
Conference_Titel :
Circuits and Systems, 2007. MWSCAS 2007. 50th Midwest Symposium on
Conference_Location :
Montreal, Que.
Print_ISBN :
978-1-4244-1175-7
Electronic_ISBN :
1548-3746
DOI :
10.1109/MWSCAS.2007.4488692
