Supervised learning based on “neurons” sensitive to similarities and dissimilarities in the stimulus features

Abstract An abstract model of a neuron is introduced that can compare stimuli by detecting similarities (S) and dissimilarities (D) in synaptic inputs. Using SD neurons in a traditional error backpropagation (BP) neural networks improves categorization and learning capability. The nonlinear combination of similar and dissimilar input features captures more extensive information about input stimuli. This guarantees more effective convergence properties when tested with XOR problems.