scientific article; zbMATH DE number 7164779

zbMath1433.68343arXiv1902.06094MaRDI QIDQ5214289

Lyudmila Grigoryeva, Juan-Pablo Ortega

Publication date: 7 February 2020

Full work available at URL: https://arxiv.org/abs/1902.06094

Title: zbMATH Open Web Interface contents unavailable due to conflicting licenses.

zbMATH Keywords

system identificationmachine learningreservoir computingVolterra series representationfinite memorystate-space systemsecho state propertyfading memory propertydifferentiable reservoir filter

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Applications of functional analysis in optimization, convex analysis, mathematical programming, economics (46N10) Approximation by other special function classes (41A30)

Related Items (12)

The echo index and multistability in input-driven recurrent neural networks ⋮ Fading memory echo state networks are universal ⋮ Transport in reservoir computing ⋮ Approximation bounds for random neural networks and reservoir systems ⋮ Designing universal causal deep learning models: The geometric (Hyper)transformer ⋮ Embedding and approximation theorems for echo state networks ⋮ Stability and memory-loss go hand-in-hand: three results in dynamics and computation ⋮ The universal approximation property. Characterization, construction, representation, and existence ⋮ Dimension reduction in recurrent networks by canonicalization ⋮ Unnamed Item ⋮ Embedding information onto a dynamical system ⋮ Memory and forecasting capacities of nonlinear recurrent networks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• On weighted Banach sequence spaces
• Reservoir computing approaches to recurrent neural network training
• A new approach to equations with memory
• Expressive power of first-order recurrent neural networks determined by their attractor dynamics
• A fixed-point farrago
• Manifolds, tensor analysis, and applications.
• Time-delay neural networks, Volterra series, and rates of approximation
• A note on representation theorems for linear discrete-space systems
• Bifurcation of relative equilibria in mechanical systems with symmetry
• Memory in linear recurrent neural networks in continuous time
• Notes on fading-memory conditions
• The dynamic universality of sigmoidal neural networks
• A representation theorem for linear discrete-space systems
• Embedding and approximation theorems for echo state networks
• Echo state networks are universal
• On the general theory of fading memory
• The Asymptotic Performance of Linear Echo State Neural Networks
• Necessary and sufficient conditions for stable synchronization in random dynamical systems
• Fading memory and the problem of approximating nonlinear operators with Volterra series
• Persistence and stability of relative equilibria
• Persistance d’orbites périodiques relatives dans les systèmes hamiltoniens symétriques
• Persistence and smoothness of critical relative elements in Hamiltonian systems with symmetry
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Bounds for discrete-time Volterra series representations
• Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
• Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
• Nonlinear Memory Capacity of Parallel Time-Delay Reservoir Computers in the Processing of Multidimensional Signals
• The Dynamics of Random Difference Equations Is Remodeled by Closed Relations
• Linear Stochastic Systems

This page was built for publication: