The use of noise-tolerant coding in modern communication systems remains the only means of increasing the efficient energy of such systems. This parameter tends to increase in conditions when the receiver of the communication system is able to correct errors of a large multiplicity. At the same time, the existing experience of using various methods for decoding the received data to achieve such a goal in the format of algebraic or iterative procedures does not give a noticeable effect and leads to a large time cost and an exponential increase in the complexity of implementing the decoder processor. The reason for this situation is the passive position of the receiver, which, when processing each code vector, remains a fixator of the picture that occurred in the communication channel and, in general, by compiling a system of linear equations and then solving it, tries to identify the error vector. Some exceptions are permutation decoding systems, which, by selecting and using reliable characters from the number received at the reception, simulate the operation of their transmitter and compare the received (almost error-free) result of such encoding with the received combination [1, 2]. With the growing influence of destructive factors, such methods are ineffective. A natural question arises: are modern solutions in neural network technologies capable of improving the characteristics of code vector recognition systems in order to obtain acceptable machine time costs in order to achieve an increase in the energy characteristics of communication systems.
A varying-gain ZNN model with fixed-time convergence and noise-tolerant performance for time-varying linear equation and inequality systems
