Research of the adaptation system are synchronized in phase receiving and emitting objects using artificial neural networks

The paper investigated the adaptation system are synchronized in phase receiving and emitting objects by comparison with a benchmark, by computer simulation of the system. The system is represented in the form of an artificial neural network, with subsequent training. For such representation, the composition of the optimized parameters is determined by selecting the confi-guration of the artificial neural network. In this case, the system is synchronized in phase receiving and emitting objects pre-sented in the form of artificial neural network nonlinearity, the corresponding definition module of a complex number. This allows adaptation by comparison with a benchmark in terms of phase distortion of a training sample. Simulations showed that, at a cer-tain value of the phase distortion, the modified algorithm has the advantage over the known method of least squares.