Learning and Generalization in Layered Neural Networks: The Contiguity Problem

The problem of inductive inference refers to extracting general rules, learning concepts from a training set consisting of some fraction of the total number of possible examples of the concept. This work explores the ability of a highly connected, layered network of simple analog processing units to perform such tasks. The problem as posed is ill-defined, since there are in general many concepts consistent with a given training set.