Modularity: a natural choice for improving generalization.
    To appear in: Proceedings of WSES'2002 International conference on Neural Networks applications.

     Leonardo Franco
Cognitive Neuroscience Sector
SISSA - Trieste - Italy

and

Jose M. Jerez
Depto. de lenguajes y Cs. de la Computacion
Univ. de Malaga
Malaga - SPAIN
 

One of the principal motivations for constructing artificial modular
neural networks comes from biological neural systems, where modularity can be observed at different levels of organization. Starting
from some theoretical results that roughly state that modular architectures generalize better than their monolithic counterparts, we test through simulations this assertion on three problems: the parity function
and other two ``real world" problems as face expression recognition and diabetes diagnosis. We also  analyze how the size of the networks influences the generalization ability. From the results we extract some general recommendations on how to build and train modular architectures.