Python Programming for Biology: Bioinformatics and Beyond

Figure 24.5.  Components of a feed-forward artificial neural network. The

organisation of nodes in a three-layer artificial neural network (left) where the node in

each layer is connected to all the nodes in the next layer, albeit with different connection

strengths. The hyperbolic tangent is often used as a trigger function to modulate each

node’s output (right). For the trigger function the x axis corresponds to the total input,

which is the weighted sum of the inputs from all the connections. The y axis represents the

node output that may be sent to the next layer.