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.<<ETX>>

[1]  Patrick F. Castelaz,et al.  Neural Network Signal Processor (NSP) , 1988, Photonics West - Lasers and Applications in Science and Engineering.

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  R. Hecht-Nielsen.  Nearest matched filter classification of spatiotemporal patterns. , 1987, Applied optics.

[4]  Terrence J. Sejnowski,et al.  NETtalk: a parallel network that learns to read aloud , 1988 .

[5]  David Zipser,et al.  Feature Discovery by Competive Learning , 1986, Cogn. Sci..

[6]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[7]  Stephen Grossberg,et al.  Studies of mind and brain , 1982 .

[8]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.