2012 | OriginalPaper | Buchkapitel
Solving the Ill-Conditioning in Neural Network Learning
verfasst von : Patrick van der Smagt, Gerd Hirzinger
Erschienen in: Neural Networks: Tricks of the Trade
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
In this paper we investigate the feed-forward learning problem. The well-known ill-conditioning which is present in most feed-forward learning problems is shown to be the result of the structure of the network. Also, the well-known problem that weights between ‘higher’ layers in the network have to settle before ‘lower’ weights can converge is addressed. We present a solution to these problems by modifying the structure of the network through the addition of linear connections which carry shared weights. We call the new network structure the
linearly augmented feed-forward network
, and it is shown that the universal approximation theorems are still valid. Simulation experiments show the validity of the new method, and demonstrate that the new network is less sensitive to local minima and learns faster than the original network.