Generalization Properties of SNN Trained with ReSuMe
Filip Ponulak, Andrzej Kasiński
Proceedings of the European Symposium on Artificial Neural Networks, ESANN’2006, Bruges, Belgium (2006) .
2006
Full text: https://www.elen.ucl.ac.be/Proceedings/esann/esannpdf/es2006-135.pdf
Abstract
In this paper we demonstrate the generalization property of spiking neurons trained with ReSuMe method. We show in a set of experiments that the learning neuron can approximate the input-output transformations defined by another - reference neuron with a high precision and that the learning process converges very quickly. We discuss the relationship between the neuron I/O properties and the weight distribution of its input connections. Finally, we discuss the conditions under which the neuron can approximate some given I/O transformations.
Notice: Undefined index: publicationsCaching in /www/html/epistemio/application/controllers/PublicationController.php on line 2240
Share comment