In automatic target recognition we often face a problem in having to train a large neural network upon a very limited data set. This paper presents methods designed to analyze trained networks. The methods allow us to investigate how the network makes its decisions as well as its generalization properties. The methods interact with each other and are intended to be used as a complete set. They use techniques of sensitivity analysis, linear algebra, and rule extraction. They have been coded in Matlab as a toolbox and tested on a large number of real networks.
Evaluation of neural networks for automatic target recognition
1997 IEEE Aerospace Conference ; 3 ; 423-439 vol.3
1997-01-01
1249931 byte
Conference paper
Electronic Resource
English
Evaluation of Neural Networks for Automatic Target Recognition
British Library Conference Proceedings | 1997
|Neural networks for automatic target recognition
Tema Archive | 1990
|Automatic target recognition for naval traffic control using neural networks
British Library Online Contents | 1998
|Automatic target recognition using neural networks (invited Paper) [3466-37]
British Library Conference Proceedings | 1998
|