Machine learning based MoM (ML-MoM) for parasitic capacitance extractions

Abstract

This paper is a rethinking of the conventional method of moments (MoM) using the modern machine learning (ML) technology. By repositioning the MoM matrix and unknowns in an artificial neural network (ANN), the conventional linear algebra MoM solving is changed into a machine learning training process. The trained result is the solution. As an application, the parasitic capacitance extraction broadly needed by VLSI modeling is solved through the proposed new machine learning based method of moments (ML-MoM). The multiple linear regression (MLR) is employed to train the model. The computations are done on Amazon Web Service (AWS). Benchmarks demonstrated the interesting feasibility and efficiency of the proposed approach. According to our knowledge, this is the first MoM truly powered by machine learning methods. It opens enormous software and hardware resources for MoM and related algorithms that can be applied to signal integrity and power integrity simulations.