Constrained-neural-network architectures for target recognition
Donald R. Hush, Mary M. Moya, Shang-Ying Clark · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1992
This paper describes several different types of constraints that can be placed on multilayered feedforward neural networks which are used for automatic target recognition (ATR). We show how unconstrained networks are likely to give poor generalization on the ATR problem. We also show how the ATR problem requires a special type of classifier called a one-class classifier. The network constraints come in two forms: architectural constraints and learning constraints. Some of the constraints are used to improve generalization, while others are incorporated so that the network will be forced to perform one-class classification.