TITLE: Modeling the Behavior of BDD Complexity Using Neural Networks
AUTHORS: Azam Beg, P. Chandanna, and Ali Assi
PUBLICATION/VENUE: 4th IASTED International Conference on Circuits, Signals, and Systems, Nov 2006.
ABSTRACT:
This research work proposes a new method to estimate the Binary Decision Diagram (BDD) complexity. A feed-forward back-propagation neural network (NN) is used and a large number of randomly generated single output Boolean functions have been considered. Experimental results show good correlation between the theoretical results and those predicted by the NN model (NNM), which will give insights to the complexity of Very Large Scale Integration (VLSI)/Computer Aided Design (CAD) designs. This model demonstrates the ability of NNs to provide reliable classification of BDD complexity.
DOWNLOAD: PDF