Artificial metaplasticity MLP applied to image classification
Alexis Marcano-Cedeño, Antonio Álvarez-Vellisco, Diego Andina · 2009
In this paper we apply artificial metaplasticity to a multilayer perceptron (MLP) for image classification. Artificial metaplasticity is a novel artificial neural network (ANN) training algorithm that gives more relevance to less frequent training patterns and subtracts relevance to the frequent ones during training phase, achieving a much more efficient training, while at least maintaining the MLP performance. In this paper, we test metaplasticity MLP (MMLP) algorithm on an image standard data set: the Wisconsin breast cancer database (WBCD). WBCD is a well-used database in machine learning, ANN and signal processing. Experimental results show that MMLPs reach better accuracy than any other recent results.