A local Echo State Property through the largest Lyapunov exponent

2014/02/07 by Mathieu Galtier, Gilles Wainrib, Galtier, Mathieu +1
Computer Science · Engineering · Physics and Astronomy · #Advanced Memory and Neural Computing #Chaotic Dynamics (nlin.CD) #FOS: Physical sciences #Neural Networks and Applications #Neural Networks and Reservoir Computing #nlin.CD

paper · pdf · doi:10.48550/arxiv.1402.1619

openalex publication_date 2014/02/07 · arxiv created 2015/05/24 · arxiv updated 2015/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Echo State Networks are efficient time-series predictors, which highly depend on the value of the spectral radius of the reservoir connectivity matrix. Based on recent results on the mean field theory of driven random recurrent neural networks, enabling the computation of the largest Lyapunov exponent of an ESN, we develop a cheap algorithm to establish a local and operational version of the Echo State Property.

Citations

• Relative entropy minimizing noisy non-linear neural network to approximate stochastic processes

Related

• Empirical Analysis of the Necessary and Sufficient Conditions of the Echo State Property
• Tailoring Artificial Neural Networks for Optimal Learning
• Feature-Based Echo-State Networks: A Step Towards Interpretability and Minimalism in Reservoir Computer
• Echo State Networks as State-Space Models: A Systems Perspective
• On the Statistical Challenges of Echo State Networks and Some Potential Remedies