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

  title={Optimization and applications of echo state networks with leaky- integrator neurons},
  author={Herbert Jaeger and Mantas Lukosevicius and Dan Popovici and Udo Siewert},
  journal={Neural networks : the official journal of the International Neural Network Society},
  volume={20 3},
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 present stability conditions, introduce and investigate a stochastic gradient descent method for the optimization of the global learning… CONTINUE READING
Highly Influential
This paper has highly influenced 30 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 497 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 287 citations

498 Citations

Citations per Year
Semantic Scholar estimates that this publication has 498 citations based on the available data.

See our FAQ for additional information.