The novelty vector for the first layer ( input units to hidden units ) is determined by taking the target pattern away from the current output of the network ( the delta rule ).
22.
The head contains special functions / neurons that activate the hidden and output units ( in the GEP context, all these units are more appropriately called functional units ) and terminals that represent the input units.
23.
Before entering an LZB controlled section the driver must enable the train by entering the required information on the Driver Input Unit and enabling LZB . When enabled the train will light a " B " light.
24.
An input unit can be converted to any number of output units the outputs are specified as a " combination " by separating unit codes with a space ( " " ) or a plus ( " + " ).
25.
For a given set of ( input, target ) states, the network is trained to settle into a stable activation state with the output units in the target state, based on a given input state clamped on the input units.
