A system for using machine learning based upon Bayesian inference using a hybrid
monte carlo method to create a model for performing integrated circuit layout extraction
is disclosed. The system of the present invention has two main phases: model creation
and model application. The model creation phase comprises creating one or more
extraction models using machine-learning techniques. First, a complex extraction
problem is decomposed into smaller simpler extraction problems. Then, each smaller
extraction problem is then analyzed to identify a set of physical parameters that
fully define the smaller extraction problem. Next, complex mathematical models
are created using machine learning techniques for all of the smaller simpler extraction
problems. The machine learning is performed by first creating training data sets
composed of the identified parameters from typical examples of the smaller extraction
problem and the answers to those example extraction problems as solved using a
highly accurate physics-based field solver. Next, the system uses Bayesian inference
implemented with a Monte Carlo method to train a set of neural networks for extraction
problems. After the creation of a set of models for each of the smaller simpler
extraction problems, the machine-learning based models may be used for extraction.
