Optimization and applications of echo state networks with leaky- integrator neurons

Herbert Jaeger, Mantas Lukosevicius, Dan Popovici, Udo Siewert
Published 2007 in Neural Networks

Abstract

Standard echo state networks (ESNs) are built from simple additive units with a sigmoid activation function. Here we investigate ESNs whose reservoir units are leaky integrator units. Units of this type have individual state dynamics, which can be exploited in various ways to accommodate the network to the temporal characteristics of a learning task. We… (More)

DOI: 10.1016/j.neunet.2007.04.016

11 Figures and Tables

Topics

Citations per Year

518 Citations

Semantic Scholar estimates that this publication has 518 citations based on the available data.

See our FAQ for additional information.

Cited By

Sort by:

Learning context-aware mobile robot navigation in home environments

Davide Bacciu, Claudio Gallicchio, Alessio Micheli, Maurizio Di Rocco, Alessandro Saffiotti
IISA 2014, The 5th International Conference on…
2014

Precise Positioning of Nonsmooth Dynamic Systems Using Fuzzy Wavelet Echo State Networks and Dynamic Surface Sliding Mode Control

Seong Ik Han, Jang Myung Lee
IEEE Transactions on Industrial Electronics
2013

A learning system for automatic Berg Balance Scale score estimation

Davide Bacciu, Stefano Chessa, +8 authors Oberdan Parodi
Eng. Appl. of AI
2017

Comparison of echo state network output layer classification methods on noisy data

Ashley A. Prater
2017 International Joint Conference on Neural…
2017

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

Qianli Ma, Lifeng Shen, Garrison W. Cottrell
ArXiv
2017

Ambient intelligence in assisted living environments

Filippo Palumbo, Stefano Chessa
2016

Preliminary Experimental Analysis of Reservoir Computing Approach for Balance Assessment

Claudio Gallicchio, Alessio Micheli, Luca Pedrelli, Federico Vozzi, Oberdan Parodi
AALTD@PKDD/ECML
2015

Effect of hybrid circle reservoir injected with wavelet-neurons on performance of echo state network

Hongyan Cui, Chen Feng, Yuan Chai, Ren-ping Liu, Yunjie Liu
Neural Networks
2014

Output-Tracking-Error-Constrained Robust Positioning Control for a Nonsmooth Nonlinear Dynamic System

Seong Ik Han, Jang Myung Lee
IEEE Transactions on Industrial Electronics
2014

Reservoir Computing with high non-linear separation and long-term memory for time-series data analysis

John B. Butcher
2012

References

Sort by:

Showing 1-10 of 29 references

H. Jaeger
GMD - German National Research Institute for…
2001

The elements of statistical learning: data mining, inference, and prediction, 2nd Edition

Trevor J. Hastie, Robert Tibshirani, Jerome H. Friedman
Springer series in statistics
2009

A tighter bound for the echo state property

Michael R. Buehner, Peter Michael Young
IEEE Transactions on Neural Networks
2006

Computational Aspects of Feedback in Neural Circuits

Wolfgang Maass, Prashant Joshi, Eduardo D. Sontag
PLoS Computational Biology
2006

TimeWarping Invariant Echo State Networks

Mantas Lukoševičius, Dan Popovici, Herbert Jaeger, Udo Siewert
2006

A learning rule for the emergence of stable dynamics and timing in recurrent networks.

Dean V Buonomano
Journal of neurophysiology
2005

A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach

Herbert Jaeger
2005

Analyzing the weight dynamics of recurrent learning algorithms

Ulf D. Schiller, Jochen J. Steil
Neurocomputing
2005

2004

Optimization and applications of echo state networks with leaky- integrator neurons

Abstract

11 Figures and Tables

Topics

Statistics

518 Citations

Cited By

Learning context-aware mobile robot navigation in home environments

Precise Positioning of Nonsmooth Dynamic Systems Using Fuzzy Wavelet Echo State Networks and Dynamic Surface Sliding Mode Control

A learning system for automatic Berg Balance Scale score estimation

Comparison of echo state network output layer classification methods on noisy data

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

Ambient intelligence in assisted living environments

Preliminary Experimental Analysis of Reservoir Computing Approach for Balance Assessment

Effect of hybrid circle reservoir injected with wavelet-neurons on performance of echo state network

Output-Tracking-Error-Constrained Robust Positioning Control for a Nonsmooth Nonlinear Dynamic System

Reservoir Computing with high non-linear separation and long-term memory for time-series data analysis

References

The ”echo state” approach to analysing and training recurrent neural networks (GMD Report No. 148)

The elements of statistical learning: data mining, inference, and prediction, 2nd Edition

A tighter bound for the echo state property

Computational Aspects of Feedback in Neural Circuits

TimeWarping Invariant Echo State Networks

A learning rule for the emergence of stable dynamics and timing in recurrent networks.

A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach

Analyzing the weight dynamics of recurrent learning algorithms

Finding good echo state networks to control

Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication.

Presentations referencing similar topics

Optimization and applications of echo state networks with leaky- integrator neurons

Abstract

11 Figures and Tables

Topics

Statistics

518 Citations

Cited By

Learning context-aware mobile robot navigation in home environments

Precise Positioning of Nonsmooth Dynamic Systems Using Fuzzy Wavelet Echo State Networks and Dynamic Surface Sliding Mode Control

A learning system for automatic Berg Balance Scale score estimation

Comparison of echo state network output layer classification methods on noisy data

Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework

Ambient intelligence in assisted living environments

Preliminary Experimental Analysis of Reservoir Computing Approach for Balance Assessment

Effect of hybrid circle reservoir injected with wavelet-neurons on performance of echo state network

Output-Tracking-Error-Constrained Robust Positioning Control for a Nonsmooth Nonlinear Dynamic System

Reservoir Computing with high non-linear separation and long-term memory for time-series data analysis

References

The ”echo state” approach to analysing and training recurrent neural networks (GMD Report No. 148)

The elements of statistical learning: data mining, inference, and prediction, 2nd Edition

A tighter bound for the echo state property

Computational Aspects of Feedback in Neural Circuits

TimeWarping Invariant Echo State Networks

A learning rule for the emergence of stable dynamics and timing in recurrent networks.

A tutorial on training recurrent neural networks , covering BPPT , RTRL , EKF and the " echo state network " approach

Analyzing the weight dynamics of recurrent learning algorithms

Finding good echo state networks to control

Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication.

Similar Papers

Presentations referencing similar topics