Neural network for reconstruction of signal from di stributed measuring system of optical amplitude sensors
А. V. Panov · 2001
A computer model of the feed-forward neural network with the hidden layer is developed to reconstruct physical field investigated by the fiber-optic measuring system of amplitude sensors. Neural network is learned by er ror backpropagation using the conjugate gradient minimizati on of deviation. Learned neural network reconstruct s the twodimensional scalar physical field with distribution having one or two Gaussian peaks.