Abstract:
An elementary introduction to the theory of artificial neuron networks is given. Principles of their structural composition are presented. Methods for the neural networks training commonly used for different levels of intellectual control of mechatronic systems are formulated and substantiated. Neuron networks approaches to typical problems of classification, digital signal processing, data compression, function interpolation and extrapolation, associative behavior, and optimization are stated.
Fulltext:
PDF file (223 kB)