论文信息 - A collective computation approach to automatic target recognition

A collective computation approach to automatic target recognition

A neural network associative memory is used to guide the template-matching process in a digital simulation model of a third-generation fuse. The templates are produced by analytic models of target interaction with several simultaneous sensors and are stored by means of the Hinton-Sejnowski formula in a symmetrically cross-coupled (Hopfield) network. A description is given of some salient features of network design and simulation. The performance gain that can be achieved with this collective computation approach is limited mainly by the size of the network.<<ETX>>

R. H. Baran | R. Baran

[1] J. Hemmen,et al. Nonlinear neural networks. I. General theory , 1988 .

[2] J. L. Hemmen,et al. Nonlinear neural networks. , 1986, Physical review letters.

[3] Sompolinsky,et al. Dynamics of spin systems with randomly asymmetric bonds: Ising spins and Glauber dynamics. , 1988, Physical review. A, General physics.

[4] 鈴木増雄. Time-Dependent Statistics of the Ising Model , 1965 .

[5] Geoffrey E. Hinton,et al. OPTIMAL PERCEPTUAL INFERENCE , 1983 .

[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] S.C.J. Garth,et al. Neural networks for artificial intelligence , 1989 .