Nearly orthogonal latin hypercubes for optimization algorithms

摘要

Nearly orthogonal latin hypercubes are used in optimization algorithms for creating an expanded and synthetically-generated data set to improve an initial optimization algorithm.

主权项

1. Apparatus for improving an initial optimization algorithm that uses a curve-fit small data set and expands the small data set to provide an expanded data set on which curve fitting is imposed to optimize the initial optimization algorithm comprising:
a specialized processor for generating an expanded data set of synthetic data points generated from the set of data points that is the result of creating an initial optimization algorithm using said small data set, the synthetic data points being generated using a nearly orthogonal latin hypercubes algorithm, said expanded data set of synthetic data points being used by said initial optimization algorithm to provide corrected optimization algorithm coefficients.