Constructing robust liquid state machines to process highly variable data streams

Authors:
Stefan Schliebs;Maurizio Fiasché;Nikola Kasabov
Affiliations:
Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand;Department of Mathematics, "F. Brioschi", Polytechnic Institute of Milan, Milan, Italy;Knowledge Engineering and Discovery Research Institute, Auckland University of Technology, New Zealand
Venue:
ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Year:
2012

Citing 6
Cited 2

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
Modeling individual's aging within a bacterial population using a pi-calculus paradigm

Natural Computing: an international journal
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
Improving liquid state machines through iterative refinement of the reservoir

Neurocomputing
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review

Continuous classification of spatio-temporal data streams using liquid state machines

ICONIP'12 Proceedings of the 19th international conference on Neural Information Processing - Volume Part IV
2013 Special Issue: Dynamic evolving spiking neural networks for on-line spatio- and spectro-temporal pattern recognition

Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we propose a mechanism to effectively control the overall neural activity in the reservoir of a Liquid State Machine (LSM) in order to achieve both a high sensitivity of the reservoir to weak stimuli as well as an improved resistance to over-stimulation for strong inputs. The idea is to employ a mechanism that dynamically changes the firing threshold of a neuron in dependence of its spike activity. We experimentally demonstrate that reservoirs employing this neural model significantly increase their separation capabilities. We also investigate the role of dynamic and static synapses in this context. The obtained results may be very valuable for LSM based real-world application in which the input signal is often highly variable causing problems of either too little or too much network activity.