A MODIFIED S-NEURON AND ITS APPLICATION TO SCALE-INVARIANT CLASSIFICATION

S neuron, a scale-invariant neuron, is successfully adopted in Neocogn itron to function as a local feature extractor. But, in operation its weights may be updated unboundedly. In addition, its scale-invariant p roperty will not be held when the learning patterns are noisy. In this paper, a Modified S Neuron (MSN) and its novel learning rule are intr oduced to overcome the drawbacks of S neuron. It is shown that after a n MSN learns a specific pattern set the mean of its excitatory weight converges to the scaled mean of the learned pattern set and its inhibi tory weight is equal to I, norm of the excitatory weight. Moreover, by applying MSNs a self-organizing scale-invariant classifier which is a two-layer structure with fully-connected weights is constructed. Two learning algorithms are given for training the classifier. It is demon strated that the classification rate can be improved, especially when the selectivity of MSN becomes adaptive. Finally, a simple experimenta l simulation is given for verification.