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.
Index Terms:
circuit analysis computing; modular artificial neural network models; VLSI circuits; modular neural network; MANN; process level parameters; circuit performance; optimization
Citation:
A.A. Ilumoka, "Modular artificial neural network models for simulation and optimization of VLSI circuits," ss, pp.190, 30th Annual Simulation Symposium (SS '97), 1997