Plenary Lecture

Artificial MetaPlasticity and the Challenge to train ANNS with reduced Pattern Availability


Professor Diego Andina
Head of Group for Automation in Signals and Communications (GASC)
Technical University of Madrid (UPM)
SPAIN
Email: andina@gc.ssr.upm.es

Abstract: Artificial implementation of Biological Metaplasticity property of synapses has been recently proposed by the author to improve Artificial Neural 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.

Brief Biography of the Speaker:
Diego Andina is Master in Computer Science and Communications simultaneously and with Honors by Technical University of Madrid (UPM) in 1990 and also the Ph D. degree "cum laude" by Technical University of Madrid in 1995. Presently is Head of Group for Automation in Signals and Communications (GASC), Technical University of Madrid, UPM, Spain.
His research interests are: Signal Processing & Communications Theory (including the internet end e-commerce) combined with Soft Computing techniques as Artificial Neural Networks, Fuzzy Logic, Genetic Algorithms, Adaptive Nonlinear Systems, etc. Author of more than 100 national and international publications, he has been director of more than 30 Research projects financed by National Government, European Commission or Private Institutions and Firms. He is also Associate Editorial Member of several International Journals and Transactions and has participated in the organization of more than 35 international events He is Founder and Director of the European Latino American Cooperation for Intelligent Automation and Control Network (ELACIAC International Research Network), officially recognized by the European Commission.