Generalization Techniques for Layered Neural Networks in the Classification of Remotely Sensed Images

Eihan SHIMIZU, Morito TSUTSUMI, Le Van TRUNG
1999 Doboku Gakkai Ronbunshu  
268 Ly Thuong Kiet Street, District 10th HoChiMinh City, Vietnam) In recent years, researchers have paid a lot of attention to Layered Neural Networks (LNNs) as a nonparametric approach for the classification of remotely sensed images. This paper focuses on the generalization capability of LNNs, that is, how well an LNN performs with unknown data. First, we clarify its description from the point of view of information statistics. With this discussion, we provide a feasible technique to design
more » ... e LNN in consideration of its generalization capability. Finally, we apply the proposed technique to a practical land cover classification using remotely sensed images, and demonstrate its potential.
doi:10.2208/jscej.1999.618_95 fatcat:altwkajqi5eltihife6ycs47ii