Neural α-feature detector:: Feature detection by controlling α-entropy

In this paper, we propose a neural cu-feature detector used to extract a small number of main or essential features in input patterns. Features can be detected by corp trolling cr-entropy for alpha-feature detectors. The alpha-entropy is defined by the difference between Renyi entropy and Shannon entropy. The alpha-entropy controller aims to maximize information contained in a few important alpha-feature detectors, while information for all the other feature detectors is minimized. Thus, the alpha-entropy controller can maximize and simultaneously minimize information. The neural alpha-feature detector was applied to the feature detection of twenty-six alphabet characters. Experimental results confirmed that by controlling alpha-entropy a small number of principal features can be detected, which can intuitively be interpreted.