Echo state network

From Wikipedia, the free encyclopedia

The echo state network (ESN) is a recurrent neural network with a sparsely connected hidden layer (with typically 1% connectivity). The connectivity and weights of hidden neurons are randomly assigned and are fixed. The weights of output neurons can be learned so that the network can (re)produce specific temporal pattern.

The main interest of this network is that although its behaviour is non-linear, the only parameters are the weights of the output layer. The error function is thus quadratic with respect to the parameter vector and can be differentiated easily to a linear system.

[edit] See also

• Liquid-state machine: a similar concept with generalized signal and network.

• aureservoir: an efficient C++ library for various kinds of echo state networks with python/numpy bindings.

[edit] References

• Herbert Jaeger and Harald Haas. Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication. Science 2 April 2004: Vol. 304. no. 5667, pp. 78 - 80 DOI: 10.1126/science.1091277 PDF (preprint)

• Herbert Jaeger (2007) Echo State Network. Scholarpedia.