Experimental demonstration of learning properties of a new supervised learning method for the spiking neural networks

Authors:
Andrzej Kasinski;Filip Ponulak
Affiliations:
Institute of Control and Information Engineering, Poznan University of Technology, Poznan, Poland;Institute of Control and Information Engineering, Poznan University of Technology, Poznan, Poland
Venue:
ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Year:
2005

Citing 3
Cited 6

Spiking Neuron Models: An Introduction

Spiking Neuron Models: An Introduction
Learning Temporally Encoded Patterns in Networks of SpikingNeurons

Neural Processing Letters
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation

Tempotron-Like Learning with ReSuMe

ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part II
Supervised learning in spiking neural networks with resume: Sequence learning, classification, and spike shifting

Neural Computation
Analysis of the ReSuMe Learning Process For Spiking Neural Networks

International Journal of Applied Mathematics and Computer Science - Special Section: Selected Topics in Biological Cybernetics, Special Editors: Andrzej Kasiński and Filip Ponulak
SWAT: a spiking neural network training algorithm for classification problems

IEEE Transactions on Neural Networks
Receptive field optimisation and supervision of a fuzzy spiking neural network

Neural Networks
Supervised Learning of Logical Operations in Layered Spiking Neural Networks with Spike Train Encoding

Neural Processing Letters

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this article we consider ReSuMe – a new supervised learning method for the Spiking Neural Networks. We present the results of experiments, which indicate that ReSuMe has the following properties: (1) it can learn temporal sequences of spikes and (2) model object’s I/O properties; (3) it is scalable and (4) computationally simple; (5) it is fast converging; (6) the method is independent on the used neuron models, for this reason it can be implemented in the networks with different neuron models and potentially also to the networks of biological neurons. All these properties make ReSuMe an attractive computational tool for the real-life applications such as modeling, identification and control of non-stationary, nonlinear objects, especially of the biological neural and neuro-muscular systems.