Auditory evoked potential classification by unsupervised ART 2-A and supervised fuzzy ARTMAP networks

Performance of ART 2-A, fuzzy ARTMAP and backpropagation systems on the classification of brainstem auditory evoked potentials is described. Fuzzy ARTMAP was deemed to be superior based on the criteria of both speed and high generalization. Higher generalization obtained with the fuzzy ARTMAP system was largely the result of a voting strategy which pooled information across individual simulations with different orderings of a given training set.<
>