MEE with Continuous Errors
The present chapter analyzes the behavior of classifiers characterized by continuous distributions of the errors, which are trained to minimize errorentropy functionals, namely the Shannon and Rényi’s quadratic entropies, presented in the preceding chapter. The analysis focus mainly the classifier problem (does the MEE solution correspond to the min P e solution?), but consistency and generalization issues are also addressed.
KeywordsShannon Entropy Gradient Ascent Gaussian Input Quadratic Entropy Error Entropy
Unable to display preview. Download preview PDF.