Neural networks in defense applications

The author presents early results of preliminary experimental investigations of the performance of various trainable (back-propagation) networks applied to sensor signal processing and optimization processing problems. Various network topologies and target signatures were exercised. Networks ranged from two-layer to six-layer, with varying number of neurons per layer. Multiple training and test sets were synthesized and used in evaluating both the training characteristics and processing performance of the various networks. Preliminary results for learning networks in pattern recognition applications indicate very promising performance characteristics for fairly simple back-propagation networks, on the order of less than 50 neurons, as a function of topology, learning rate, and sensor signal complexity. Overall, the networks behaved as expected for back-propagation networks.<>