Generalization of Rules by Neural Nets (original) (raw)

Europhysics Letters (EPL), 1992

Abstract

Abstract.-We investigate the generalization abilities of various types of rules for both feedforward and symmetric Hopfield neural network, The networks of the size of 24 neurons are taught to perform the rule on a small set of examples using simulated annealing optimization. Results show a rather small dependence of the type of network, but a significant difference in generalizing different rules is found. This suggests the possibility of defining the complexity of a rule to a certain extent independently of physical ...

Giorgio Parisi hasn't uploaded this paper.

Let Giorgio know you want this paper to be uploaded.

Ask for this paper to be uploaded.