
Fundamentals of Soft ComputingFundamentals of Soft Computing 21
2. Multilayer feedforward network. Figure 1.11 shows a network example
of this category, this kind of network have one or more hidden layers,
each hidden layer is composed by hidden neurons. The function of the
hidden layers is to interact between external inputs to the network,
and the network outputs. The more hidden layers have a network
the higher statistic features can be extracted. The network shown in
the fi gure is a fully connected feedforward network with one input
layer with “m” source nodes (m), two hidden layers with two hidden
nodes (h
1
and h
2
), and one output layer ...