In this paper we present a rigorous definition of classification in a common family of models for the mammalian vision system, and provide a formal analysis of classification power in this family. We characterize the power of a single unit, and subsequently demonstrate how to reduce a network of arbitrary topology and size to such a single unit. We finally show how such a network, via a reduction to a single unit, is equivalent to a simple 3 layer feed forward network of threshold units.
展开▼