A SCALE-INVARIANT FEATURE MAP

We use a simple network which uses negative feedback of activation and simple Hebbian learning to self-organize in such a way as to produce a hierarchical classification network. By adding neighbourhood relatio ns to its learning rule, we create a feature map which has the propert y of retaining the angular properties of the input data? i.e. vectors of similar directions are classified similarly regardless of their mag nitude. We use neither renormalization of weights nor data preprocessi ng in the network despite using competition based on maximizing the ne uron's activation.