Bearing estimation using neural optimisation methods

Abstract
The bearing estimation problem is mapped onto the Liapunov energy function of the Hopfield model neural network. However, the Hopfield model implements a gradient descent algorithm, and, in common with all such algorithms, it is liable to find a local minimum rather than the desired global minimum. To overcome this problem three modifications, gain annealing, iterated descent, and stochastic networks, have been proposed. The modifications to the neural algorithm are outlined and simulated, and results are presented to show their convergence properties in the context of the bearing estimation problem.<>

This publication has 11 references indexed in Scilit: