Use of the separation property to derive Liquid State Machines with enhanced classification performance

Authors:
Emmanouil Hourdakis;Panos Trahanias
Affiliations:
Institute of Computer Science, Foundation for Research and Technology - Hellas (FORTH), Heraklion, Greece and Department of Computer Science, University of Crete, Heraklion, Greece;Institute of Computer Science, Foundation for Research and Technology - Hellas (FORTH), Heraklion, Greece and Department of Computer Science, University of Crete, Heraklion, Greece
Venue:
Neurocomputing
Year:
2013

Citing 8
Cited 0

Spikes: exploring the neural code

Spikes: exploring the neural code
Real-time computing without stable states: a new framework for neural computation based on perturbations

Neural Computation
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Movement prediction from real-world images using a liquid state machine

Applied Intelligence
2007 Special Issue: Edge of chaos and prediction of computational performance for neural circuit models

Neural Networks
A learning rule for very simple universal approximators consisting of a single layer of perceptrons

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

Neurocomputing
An introduction to simulated evolutionary optimization

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.01

Visualization

Abstract

Liquid State Machines constitute a powerful computational tool for carrying out complex real time computations on continuous input streams. Their performance is based on two properties, approximation and separation. While the former depends on the selection of class functions for the readout maps, the latter needs to be evaluated for a particular liquid architecture. In the current paper we show how the Fisher's Discriminant Ratio can be used to effectively measure the separation of a Liquid State Machine. This measure is then used as a fitness function in an evolutionary framework that searches for suitable liquid properties and architectures in order to optimize the performance of the trained readouts. Evaluation results demonstrate the effectiveness of the proposed approach.