Complex-valued Hopfield Neural Network for Amplitude Estimation of Sinusoidal Signals

Recently models of neural networks that can directly deal with complex numbers, complex-valued neural networks, have been proposed and several studies on their abilities of information processing have been done. In this paper, the problem of amplitude estimation of sinusoidal signals from observations corrupted by colored noise using Hopfield neural network (HNN) is considered. We have introduce a complex Hopfield neural networks which can be expressed as an equivalent real valued networks by expanding its real and imaginary parameters separatly. To prove the efficient of the proposed method, it has been compared with various amplitude estimator cited in [4]. Simulation results show that the calculation precision of the amplitudes estimation improves when the mean-squared error is used.