Figure 1: Feedforward multilayer perceptron for time series prediction
Artificial neural networks consist of simple calculation elements,
called neurons, and weighted connections between them.
In a feedforward multilayer perceptron (figure 
) the neurons are distributed in layers
and a neuron from one layer is fully connected only to each neuron of
the next layer.
Values are given to the neurons in the input layer; the results are taken from the output layer.
The outputs of the input neurons are propagated through the hidden layers of the net.
Such a feedforward multilayer perceptron can approximate any function after a suitable amount of training. For that discrete values of this function are presented to the net. The net is expected to learn the function rule. The behaviour of the net is changed by modification of the weights and bias values.