Abstract: A machine learning optimizer that runs a simulator uses time-state waves as input to determine initial node values for the simulator in an official simulation run, producing time state waves as a result. A learning model uses the input and output as a training example by reversing the time-state waves, using the output from the simulator as input, obtains output, reversed the output, and then uses the reversed output as ground truth to compare to desired output of the simulation.

Abstract: A simulator is run using a learning model to generate starting values for the nodes in the simulator. After the simulation has run, a cost is determined for the run. When the cost is within a threshold, the learning model results are used as starting values for an optimizer that will be used to generate starting values for the nodes in the simulator. Then, the optimizer is iteratively run such that for each iteration, results of running the optimizer are used as training input into the learning model.