Transitions in echo index and dependence on input repetitions

DOI10.1016/J.PHYSD.2024.134277MaRDI QIDQ6584209

Peter Ashwin, Andrea Ceni

Publication date: 6 August 2024

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

zbMATH Keywords

recurrent neural networknonautonomous dynamical systemmultistabilityecho state propertyinput-driven system

Mathematics Subject Classification ID

Stability of topological dynamical systems (37B25) Reasoning under uncertainty in the context of artificial intelligence (68T37) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Gradient-like behavior; isolated (locally maximal) invariant sets; attractors, repellers for topological dynamical systems (37B35) Topological dynamics of nonautonomous systems (37B55)

Cites Work

• Title not available (Why is that?)
• Title not available (Why is that?)
• Reservoir computing approaches to recurrent neural network training
• The echo index and multistability in input-driven recurrent neural networks
• Optimization and applications of echo state networks with leaky- integrator neurons
• Symbolic Dynamics and its Applications
• An Introduction to Symbolic Dynamics and Coding
• An Introduction to Symbolic Dynamics and Coding
• Opening the Black Box: Low-Dimensional Dynamics in High-Dimensional Recurrent Neural Networks
• Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
• Topological and Ergodic Theory of Symbolic Dynamics

This page was built for publication: Transitions in echo index and dependence on input repetitions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6584209)