In this article we study the effects of introducing structure in the input distribution of the data to be learnt by a simple perceptron. We determine the learning curves within the framework of Statistical Mechanics. Stepwise generalization occurs as a function of the number of examples when the distribution of patterns is highly anisotropic. Although… (More)
We study the typical properties of polynomial Support Vector Machines within a Statistical Mechanics approach that allows us to analyze the eeect of diierent normalizations of the features. If the normalization is adecuately chosen, there is a hierarchical learning of features of increasing order as a function of the training set size.