A constrained regularization approach for input-driven recurrent neural networks

DOI10.1007/s12591-010-0067-xzbMath1257.39006MaRDI QIDQ691290

Jochen J. Steil, R. Felix Reinhart

Publication date: 30 November 2012

Published in: Differential Equations and Dynamical Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s12591-010-0067-x

zbMATH Keywords

regularization; recurrent neural networks; reservoir computing

Mathematics Subject Classification ID

34B15: Nonlinear boundary value problems for ordinary differential equations

76S05: Flows in porous media; filtration; seepage

39A12: Discrete version of topics in analysis

Uses Software

• Evolino

Cites Work

• Unnamed Item
• On global asymptotic stability of a class of nonlinear systems arising in neural network theory
• Local stability of recurrent networks with time-varying weights and inputs
• Optimization and applications of echo state networks with leaky- integrator neurons
• Online reservoir adaptation by intrinsic plasticity for backpropagation-decorrelation and echo state learning
• An experimental unification of reservoir computing methods
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• New conditions for global stability of neural networks with application to linear and quadratic programming problems
• Asymptotic properties of incrementally stable systems
• Analysis and Design of Echo State Networks