Design strategies for weight matrices of echo state networks

DOI10.1162/NECO_A_00374MaRDI QIDQ2840892zbMATH OpenDBLPWikidataFDO

Authors Tobias Strauss, Welf Wustlich, Roger Labahn

Publication date 23 July 2013

Published in Neural Computation (Search for Journal in Brave)

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Systems biology, networks (92C42) Neural networks for/in biological studies, artificial life and related topics (92B20) Special matrices (15B99)

Recommendations

• Re-visiting the echo state property
• Analysis and Design of Echo State Networks
• The architecture of dynamic reservoir in the echo state network
• Echo state property linked to an input: exploring a fundamental characteristic of recurrent neural networks
• An experimental unification of reservoir computing methods

Cites work

• Analysis and Design of Echo State Networks
• Reservoir computing approaches to recurrent neural network training

Cited in

(5)

• Echo state wavelet network with small-world scale-free characteristics
• Analysis and Design of Echo State Networks
• Echo state network with multiple delayed outputs for multiple delayed time series prediction
• Short-term memory capacity in networks via the restricted isometry property
• Dynamical systems as temporal feature spaces

This page was built for publication: Design strategies for weight matrices of echo state networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2840892)