Stable Output Feedback in Reservoir Computing Using Ridge Regression

Authors:
Francis Wyffels;Benjamin Schrauwen;Dirk Stroobandt
Affiliations:
Electronics and Information Systems Department, Ghent University, Belgium;Electronics and Information Systems Department, Ghent University, Belgium;Electronics and Information Systems Department, Ghent University, Belgium
Venue:
ICANN '08 Proceedings of the 18th international conference on Artificial Neural Networks, Part I
Year:
2008

Citing 4
Cited 10

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

Neural Computation
2007 Special Issue: Optimization and applications of echo state networks with leaky- integrator neurons

Neural Networks
2007 Special Issue: An experimental unification of reservoir computing methods

Neural Networks
Event detection and localization in mobile robot navigation using reservoir computing

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks

Effects of connectivity structure of complex echo state network on its prediction performance for nonlinear time series

Neurocomputing
A comparative study of Reservoir Computing strategies for monthly time series prediction

Neurocomputing
Regularization and stability in reservoir networks with output feedback

Neurocomputing
Simple deterministically constructed cycle reservoirs with regular jumps

Neural Computation
Survey: Reservoir computing approaches to recurrent neural network training

Computer Science Review
Learning to imitate YMCA with an ESN

ICANN'12 Proceedings of the 22nd international conference on Artificial Neural Networks and Machine Learning - Volume Part I
Locomotion without a brain: Physical reservoir computing in tensegrity structures

Artificial Life
Time series classification for the prediction of dialysis in critically ill patients using echo statenetworks

Engineering Applications of Artificial Intelligence
Multi-directional continuous association with input-driven neural dynamics

Neurocomputing
A novel method for training an echo state network with feedback-error learning

Advances in Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

An important property of Reservoir Computing, and signal processing techniques in general, is generalization and noise robustness. In trajectory generation tasks, we don't want that a small deviation leads to an instability. For forecasting and system identification we want to avoid over-fitting. In prior work on Reservoir Computing, the addition of noise to the dynamic reservoir trajectory is generally used. In this work, we show that high-performing reservoirs can be trained using only the commonly used ridge regression. We experimentally validate these claims on two very different tasks: long-term, robust trajectory generation and system identification of a heating tank with variable dead-time.