Madaline networks

This rule is used in the adaline layer of the adaline and madaline networks, for which the only allowed values for are +1 and -1. Weights can change even if the output is correct. 

In the madaline network, the PEs in the adaline layer compete for learning, the winner being the PE whose weighted sum is closest to zero but with the wrong output. Only the winning PE learns. The learning rate is usually set to 1. 

Figure 21 Feed-forward neural network training and testing results with Madaline III training for solvent activity predictions in polar binaries (with learning parameter 77 = 0.1 and perturb As = 0.1).

---