Modular artificial neural network models for simulation and optimization of VLSI circuits

Abstract

A method is proposed which generates a modular neural network MANN for mapping process level parameters to circuit performance. The MANN-an adaptive mixture of local experts competing to learn different aspects of a problem-is employed in performing extremely efficient optimization of the circuit yield at minimal cost. The MANN calculates circuit performance and optimizes yield with 97% accuracy at 28% of the cost of a full SPICE simulation.