Artificial metaplasticity and the challenge to train ANNS with reduced pattern availability
Diego Andina · 2007
Networks (ANN) design. This upgrade of existing models claims a much more efficient information extraction from the patterns available to train the ANN. The hypothesis has been tested as an application example in the Multilayer Perceptron (MLP) case, probably the most widely ANN applied through the ANN history. The results show a much more efficient training that is of crucial relevance when few training patterns are the only information font for the ANN design.