Structure and Threshold Functions for Neural Networks

The input value for an arbitrary unit, j, is then the sum of all activations coming from the units of the preceding layer, multiplied by the respective weights, w j, plus the bias value 0jj. Thus, the total input to unit j, will be written as (5.171) where n represents the number of the neurons preceding neuron j and Oj shows the output. 

It is not difficult to observe that the application of an ANN to a problem involves four steps  

selection of the network topology (i.e. the layout of the neurons and their inter-connections), 

specification of the transformation operator for each neuron from the topology, 

initial assignment of weights W] j, which are updated as the network learns, 

---