An experimental unification of reservoir computing methods

  title={An experimental unification of reservoir computing methods},
  author={David Verstraeten and Benjamin Schrauwen and Michiel D'Haene and Dirk Stroobandt},
  journal={Neural networks : the official journal of the International Neural Network Society},
  volume={20 3},
Three different uses of a recurrent neural network (RNN) as a reservoir that is not trained but instead read out by a simple external classification layer have been described in the literature: Liquid State Machines (LSMs), Echo State Networks (ESNs) and the Backpropagation Decorrelation (BPDC) learning rule. Individual descriptions of these techniques exist, but a overview is still lacking. Here, we present a series of experimental results that compares all three implementations, and draw… CONTINUE READING
Highly Influential
This paper has highly influenced 23 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 693 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 289 extracted citations

Architectural designs of Echo State Network

View 20 Excerpts
Highly Influenced

Simple Deterministically Constructed Cycle Reservoirs with Regular Jumps

Neural Computation • 2012
View 10 Excerpts
Highly Influenced

Engineering Applications of Neural Networks

Communications in Computer and Information Science • 2017
View 6 Excerpts
Highly Influenced

Temporal Learning Using Echo State Network for Human Activity Recognition

2016 Third European Network Intelligence Conference (ENIC) • 2016
View 15 Excerpts
Highly Influenced

Echo State Queueing Network: A new reservoir computing learning tool

2013 IEEE 10th Consumer Communications and Networking Conference (CCNC) • 2013
View 5 Excerpts
Highly Influenced

694 Citations

Citations per Year
Semantic Scholar estimates that this publication has 694 citations based on the available data.

See our FAQ for additional information.

Similar Papers

Loading similar papers…