- Recurrent neural
An echo state network is usually a standard RNN with fixed
random weights. The output from this RNN is used as a high
dimensional feature map to be fed into a machine learning
(Jaeger 2004, 2012; Jaeger, Maass, and
Jaeger, H. 2004. “Harnessing
Nonlinearity: Predicting Chaotic Systems and Saving Energy in
Wireless Communication.” Science 304 (5667):78–80.
Jaeger, Herbert. 2012. “Long Short-Term
Memory in Echo State Networks: Details of a Simulation Study.”
Jacobs University Bremen.
Jaeger, Herbert, Wolfgang Maass, and Jose
Principe. 2007. “Special Issue on Echo State Networks and Liquid
State Machines.” Neural Networks 20 (3):287–89.