COMBINING SIMILARITIES AND DISSIMILARITIES IN SUPERVISED LEARNING
Valter Rodrigues, Josef Skrzypek · International Journal of Neural Systems · 1991
Categorization, as an active phase of the visual perception, must include a stage where a currently viewed exemplar of an object is compared to the previously acquired category representatives; comparisons between exemplars as opposed to simply examining one exemplar in isolation lead to improved supervised learning. An abstract model of a neuron (SD neuron) is introduced, that can compare inputs by detecting (S)imilarities and (D)issimilarities in sequentially presented stimuli. Using SD neurons in a traditional Back Error Propagation (BP) neural networks improves categorization and learning capability. The nonlinear combination of similar and dissimilar input features captures more extensive information about stimulus. SD networks also display more effective convergence properties than BP networks when tested with XOR problems. Finally, in a comparative study of printed-letter categorization, the SD network model performed better than the traditional BP network.