Recurrent kernel machines: computing with infinite echo state networks

DOI10.1162/NECO_A_00200MaRDI QIDQ2885086zbMATH OpenOpenAlexDBLPWikidataFDO

Authors 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)

Recommendations

• Echo state networks with filter neurons and a delay\&sum readout
• Dynamical systems as temporal feature spaces
• Embedding and approximation theorems for echo state networks
• Reservoir computing approaches to recurrent neural network training
• The copula echo state network

Cites work

• An experimental unification of reservoir computing methods
• Automatic speech recognition using a predictive echo state network classifier
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Gaussian processes for machine learning.
• scientific article; zbMATH DE number 1843268 (Why is no real title available?)
• Large-margin classification in infinite neural networks
• Optimization and applications of echo state networks with leaky- integrator neurons
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Reservoir computing approaches to recurrent neural network training
• The spectral radius of large random matrices
• Training a Support Vector Machine in the Primal
• Training Recurrent Networks by Evolino

Cited in

(16)

• Direct adaptive control for nonlinear systems using a TSK fuzzy echo state network based on fractional-order learning algorithm
• Neural kernels for recursive support vector regression as a model for episodic memory
• Deep reservoir computing
• Learning grammatical structure with Echo State Networks
• A local echo state property through the largest Lyapunov exponent
• A decentralized training algorithm for echo state networks in distributed big data applications
• Reservoir computing approaches to recurrent neural network training
• Dynamical systems as temporal feature spaces
• On Kernel Method–Based Connectionist Models and Supervised Deep Learning Without Backpropagation
• Distributed sequence memory of multidimensional inputs in recurrent networks
• scientific article; zbMATH DE number 5048363 (Why is no real title available?)
• The copula echo state network
• Hybrid Parameter Search and Dynamic Model Selection for Mixed-Variable Bayesian Optimization
• A structure-preserving kernel method for learning Hamiltonian systems
• Next-generation reservoir computing for dynamical inference
• Impact of weak generalized synchronization on time series forecasting using reservoir computers

Describes a project that uses

Uses Software

• DARPA TIMIT

This page was built for publication: Recurrent kernel machines: computing with infinite echo state networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2885086)