Multilayer feed forward MLF networks

As an extension of perceptron-like networks MLF networks can be used for non-linear classification tasks. They can however also be used to model complex non-linear relationships between two related series of data, descriptor or independent variables (X matrix) and their associated predictor or dependent variables (Y matrix). Used as such they are an alternative for other numerical non-linear methods. Each row of the X-data table corresponds to an input or descriptor pattern. The corresponding row in the Y matrix is the associated desired output or solution pattern. A detailed description can be found in Refs. [9,10,12-18]. 

The general stmcture is shown in Fig. 44.9. The units are ordered in layers. There are three types of layers the input layer, the output layer and the hidden layer(s). All units from one layer are connected to all units of the following layer. The network receives the input signals through the input layer. Information is then passed to the hidden layer(s) and finally to the output layer that produces the response of the network. There may be zero, one or more hidden layers. Networks with one hidden layer make up the vast majority of the networks. The number of units in the input layer is determined by p, the number of variables in the (nxp) matrix X. The number of units in the output layer is determined by q, the number of variables in the inxq) matrix Y, the solution pattern. 

Just as in the perceptron-Iike networks, an additional column of ones is added to the X matrix to accommodate for the offset or bias. This is sometimes explicitly depicted in the structure (see Fig. 44.9b). Notice that an offset term is also provided between the hidden layer and the output layer. 

The choice of h, the number of units in the hidden layers, or hidden units, is discussed in Section 44.5.8. 

---