Cross-entropy based combination of discrete probability distributions for distributed decision making
Abstrakt
The construction and examples of the optimal estimator in locally centralized scenario with uncertainty forms the core of the thesis. In Preliminaries section contains the denitions of used divergences and principles.
In the second chapter we derive the decision rule for general prior distribution. The third chapter includes the form of the estimator for Dirichlet prior distribution, its properties and illustrative examples.
The fourth chapter gives examples of the optimal estimator when the conditional probabilities. The fth chapter focuses on comparison of the proposed approach for combining probability vectors with other methods.
The conclusion and future work plans are given in the sixth chapter