Generalization properties of spiking neurons trained with ReSuMe method

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.

• Type: Conference
• Year: 2006
• Where: ESANN
• Authors: Filip Ponulak, Andrzej J. Kasinski
• Keywords: ESANN 2006, ESANN 2007, Neuron, Neuron I/o Properties, Reference Neuron