Modeling the complexity of digital circuits using neural networks

A new neural network (NN) approach is proposed in this paper to estimate the Boolean function (BF) complexity and consequently the complexity of its digital circuit implementation. Large number of randomly generated single output BFs has been used and experimental results show good correlation between the theoretical results and those predicted by the NN model. The proposed model is capable of predicting the number of product terms (NPT) in the BF that gives an indication on its complexity. In addition, this model provides information on potential points where the BF can be simplified to the maximum and the NPT for minimum Boolean complexity. This model demonstrates also the computational capabilities of NNs, especially by providing an easy and reliable classification of the BFs complexity.