CRITIQUE OF SOME NEURAL-NETWORK ARCHITECTURES AND CLAIMS FOR CONTROL AND ESTIMATION

While there is great potential for successful use of neural network (N N) algorithms in automatic target recognition (ATR) and other pattern identification/classification applications, significant barriers have been encountered (as summarized herein) that, to date, defy rigorous u se of NNs within feedback control designs. The status of several probl ems and contradictions involving NNs relating to control and estimatio n theory applications (and to practical failure detection within INS/G PS navigation systems) are summarized here. To give a positive spin an d for a balanced perspective, we also mention many novel laudable NN r esults obtained by invoking the techniques and results of control and estimation theory.