Concept learning in Hopfield associative memories trained with noisy examples using the Hebb rule

The notion of concept learning is introduced. Here we consider a concept as the mean of some statistical distribution, from which the examples of this concept are drawn. We study, using standard probability theory results, the ability of the Hopfield model of associative memory using the Hebb rule to learn concepts from examples in the presence of noise. We state and prove properties concerning this ability.