The number of output neurons is set to 2, which is equal to the
number of classes specified in the response data.
The network has two output neurons because there
are two response values (classes) associated with
each input vector. Each output neuron represents a
class. When an input vector of the corresponding
class is applied to the network, the corresponding
neuron should generate a value of 1, and the other
neurons should generate a value of 0.