1 February 1999 Entropy optimized morphological shared-weight neural networks
Author Affiliations +
Abstract
Morphological shared-weight neural networks previously demonstrated performance superior to that of MACE filters and standard shared-weight neural networks for target detection. Empirical analysis showed that entropy measures of the morphological shared-weight networks were consistently higher than those of the standard shared-weight neural networks. Based on this observation, an entropy maximization term was added to the morphological shared-weight network objective function. In this paper, target detection results are presented for morphological shared-weight networks trained with and without entropy terms.
Mohamed A. Khabou, Mohamed A. Khabou, Paul D. Gader, Paul D. Gader, Hongchi Shi, Hongchi Shi, } "Entropy optimized morphological shared-weight neural networks," Optical Engineering 38(2), (1 February 1999). https://doi.org/10.1117/1.602085 . Submission:
JOURNAL ARTICLE
11 PAGES


SHARE
Back to Top