A new framework for modeling learning dynamics

An important issue in neural computing concerns the description of learning dynamics with macroscopic dynamical variables. Recent progress on online learning only addresses the often unrealistic case of an infinite training set. We introduce a new framework to model batch learning of restricted sets of examples, widely applicable to any learning cost function, and fully taking into account the temporal correlations introduced by the re-cycling of the examples. Here we illustrate the technique using the Adaline rule learning random of teacher-generated examples