Minimum-cross-entropy inversion, spectrum analysis, and classification. Introduction and discussion of possible geophysical applications

Abstract

The principle of minimum cross-entropy (MCE) is a general method of inference about unknown probability densities given information in the form of constraints on expected values. The background, justification, and properties of MCE inversion are summarized briefly. Some recent applications in spectrum analysis and pattern classification are then summarized, and some speculations on the application of MCE to general inversion problems in geophysics are offered.