MULTI-LAYER CORRECTIVE CASCADE ARCHITECTURE FOR ON-LINE PREDICTIVE ECHO STATE NETWORKS

Authors:
Russell Y. Webb
Affiliations:
University of Canterbury, Electrical and Computer Engineering, New Zealand
Venue:
Applied Artificial Intelligence
Year:
2008

Citing 5
Cited 2

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

Neural Networks
2007 Special Issue: Decoupled echo state networks with lateral inhibition

Neural Networks
Short term memory and pattern matching with simple echo state networks

ICANN'05 Proceedings of the 15th international conference on Artificial Neural Networks: biological Inspirations - Volume Part I
Merging echo state and feedforward neural networks for time series forecasting

ICANN'06 Proceedings of the 16th international conference on Artificial Neural Networks - Volume Part I
A tighter bound for the echo state property

IEEE Transactions on Neural Networks

Time Series Prediction with Evolved, Composite Echo State Networks

SEAL '08 Proceedings of the 7th International Conference on Simulated Evolution and Learning
Training Methods and Analysis of Composite, Evolved, On-Line Networks for Time Series Prediction

IWANN '09 Proceedings of the 10th International Work-Conference on Artificial Neural Networks: Part I: Bio-Inspired Systems: Computational and Ambient Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

An architecture for on-line learning of time series prediction is presented which uses a series of echo state networks (ESNs). Each ESN learns to predict an error correction term for the previous ESN. This technique is demonstrated to improve prediction accuracy for on-line learning of the Mackey-Glass chaotic oscillator. The results are compared to other architectural configurations to show that the improved performance emerges from sequential ESN error correction. A new recurrent network structure is shown to be a useful simplification of the usual ESN reservoir.