Multistate combination approaches for liquid state machine in supervised spatiotemporal pattern classification

Authors:
FrançOis RhéAume;Dominic Grenier;íLoi Bossé
Affiliations:
Defence R&D Canada - Valcartier, Quéébec, Quebec, Canada and Dept. de Génie Electrique et Génie Informatique, Université Laval, Québec, Quebec, Canada;Dept. de Génie Electrique et Génie Informatique, Université Laval, Québec, Quebec, Canada;Defence R&D Canada - Valcartier, Quéébec, Quebec, Canada and Dept. de Génie Electrique et Génie Informatique, Université Laval, Québec, Quebec, Canada
Venue:
Neurocomputing
Year:
2011

Citing 12
Cited 0

Computing with spiking neurons

Pulsed neural networks
Pulsed Neural Networks

Pulsed Neural Networks
Spiking Neuron Models: An Introduction

Spiking Neuron Models: An Introduction
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
Machine Learning for Sequential Data: A Review

Proceedings of the Joint IAPR International Workshop on Structural, Syntactic, and Statistical Pattern Recognition
Vehicle classification in distributed sensor networks

Journal of Parallel and Distributed Computing
EEG Signal Classification Using Wavelet Feature Extraction and Neural Networks

JVA '06 Proceedings of the IEEE John Vincent Atanasoff 2006 International Symposium on Modern Computing
Movement prediction from real-world images using a liquid state machine

Applied Intelligence
Long Short-Term Memory

Neural Computation
Liquid Computing

CiE '07 Proceedings of the 3rd conference on Computability in Europe: Computation and Logic in the Real World
Unsupervised clustering with spiking neurons by sparse temporal coding and multilayer RBF networks

IEEE Transactions on Neural Networks
Which model to use for cortical spiking neurons?

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Liquid state machine is a recent concept whose aptitude for spatiotemporal pattern recognition tasks has already been demonstrated. It consists in stimulating an untrained spiking neural network with input streams, creating complex dynamics that form the liquid state. An external function, the readout, is trained to map the liquid states into the desired outputs. In this paper, different avenues are explored to improve the classification performance of the readout. First are compared the membrane potentials and the firing rates of the neurons as two different liquid state representations. We also propose a new liquid state representation based on the frequency components of short-time membrane potential signals. Tests on synthetic and real data reveal that the frequency-based representation gets higher recognition rates than by using membrane potential or firing rates. Finally, we show that the combination of the different liquid states can improve the classification performance on spatiotemporal data.