Pavel Praht: Good afternoon . I wanted to know - your neural corresponds to linear development and the network consists of an input layer and an output layer. Accordingly, independent and dependent variables are supplied. The input data is converted by network neurons and compared with the output. If the deviation is greater than the specified one, then the weights of the neuron bonds between each other and the threshold values of the neurons change in a special way. Again, the process of calculating the output value occurs and its comparison with the standard. If the deviation is less than the specified error, then the learning process stops?
Stephen Thaler: Good night! Pavel, You've just described back propagation. So what is the question? What you see here is much more.