MODEL-BASED NEURAL-NETWORK FOR TARGET DETECTION IN SAR IMAGES

A controversial issue in the research of mathematics of intelligence h as been that of the roles of a priori knowledge versus adaptive learni ng, After discussing mathematical difficulties of combining a priority with adaptivity encountered in the past, we introduce a concept of a model-based neural network, whose adaptive learning is based on a prio ri models. Applications to target detection in SAR images are discusse d, We briefly overview the SAR principles, derive relatively simple ph ysics-based models of SAR signals, and describe model-based neural net works that utilize these models. A number of real-world application ex amples are presented.