Recurrent Kernel Machines: Computing with Infinite Echo State Networks

DOI10.1162/NECO_a_00200zbMath1238.68125OpenAlexW2090722674WikidataQ43784190 ScholiaQ43784190MaRDI QIDQ2885086

Michiel Hermans, Benjamin Schrauwen

Publication date: 21 May 2012

Published in: Neural Computation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1162/neco_a_00200

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20)

Related Items

Neural kernels for recursive support vector regression as a model for episodic memory ⋮ A local echo state property through the largest Lyapunov exponent ⋮ On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation ⋮ Direct adaptive control for nonlinear systems using a TSK fuzzy echo state network based on fractional-order learning algorithm

Uses Software

• DARPA TIMIT

Cites Work

• Unnamed Item
• Unnamed Item
• Reservoir computing approaches to recurrent neural network training
• The spectral radius of large random matrices
• Optimization and applications of echo state networks with leaky- integrator neurons
• An experimental unification of reservoir computing methods
• Automatic speech recognition using a predictive echo state network classifier
• Large-Margin Classification in Infinite Neural Networks
• Training Recurrent Networks by Evolino
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Training a Support Vector Machine in the Primal