Optimization of learning the neuronetworking data processing system for non-satinary objects recognition and forecasting

The problem of construction the neuronetworking systems for non-stationary information adaptive processing at various practical applications is formulated. The developed methods and algorithms of neural network training subset formation allow to take into account the conditions of information transfer, variation of statistical parameters and dynamic properties of data. The controlling algorithms which process the data with continuous nature are developed by criteria of minimal mean-squared error. The models and algorithms are offered for optimization and neurosystem learning.