- tags
- Recurrent neural networks, Unsupervised learning
- resources
- Scholarpedia
Principle
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 system.
(Jaeger 2004, 2012; Jaeger, Maass, and Principe 2007)
Bibliography
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.