Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers

DOI10.1016/J.PHYSD.2023.133956arXiv2211.09515OpenAlexW4388979188MaRDI QIDQ6118141

Allen Hart

Publication date: 23 February 2024

Published in: Physica D (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2211.09515

zbMATH Keywords

embeddingreservoir computinggeneralised synchronisation

Mathematics Subject Classification ID

Computational learning theory (68Q32) Learning and adaptive systems in artificial intelligence (68T05) Strange attractors, chaotic dynamics of systems with hyperbolic behavior (37D45)

Cites Work

• Embedology
• The synchronization of chaotic systems
• Embedding and approximation theorems for echo state networks
• Echo state networks trained by Tikhonov least squares are \(L^2(\mu)\) approximators of ergodic dynamical systems
• Alternative way to derive the distribution of the multivariate Ornstein-Uhlenbeck process
• The echo index and multistability in input-driven recurrent neural networks
• Echo state networks are universal
• Optimization and applications of echo state networks with leaky- integrator neurons
• Differential Topology
• Regularity of invariant graphs for forced systems
• Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
• Deterministic Nonperiodic Flow
• Fundamentals of synchronization in chaotic systems, concepts, and applications
• Embedding information onto a dynamical system
• Fading memory echo state networks are universal

This page was built for publication: Generalised synchronisations, embeddings, and approximations for continuous time reservoir computers