Self-organized learning in multi-layer networks

Presents a framework for the self-organized formation of high level learning by a statistical preprocessing of features. The paper focuses first on the formation of the features in the context of layers of feature processing units as a kind of resource-restricted associative learning. The author claims that such an architecture must reach maturity by basic statistical proportions, optimizing the information processing capabilities of each layer. The final symbolic output is learned by pure association of features of different levels and kind of sensorial input. Finally, the author also shows that common error-correction learning can be accomplished by a kind of associative learning