Bearing estimation using neural networks

Two modifications to the neural-network algorithm originally proposed by J.J. Hopfield (1982), gain annealing and iterated descent, are proposed that yield better convergence to the global minimum. Simulation results are presented to illustrate the performance of the proposed algorithm for bearing estimation.<<ETX>>

[1]  I. Reed,et al.  Rapid Convergence Rate in Adaptive Arrays , 1974, IEEE Transactions on Aerospace and Electronic Systems.

[2]  E. Baum.  Towards practical `neural' computation for combinatorial optimization problems , 1987 .

[3]  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.

[4]  T. Durrani,et al.  A comparative study of modern eigenstructure methods for bearing estimation-A new high performance approach , 1986, 1986 25th IEEE Conference on Decision and Control.

[5]  Ramdas Kumaresan,et al.  Array signal processing with interconnected Neuron-like elements , 1987, ICASSP '87. IEEE International Conference on Acoustics, Speech, and Signal Processing.