The echo index and multistability in input-driven recurrent neural networks
DOI10.1016/j.physd.2020.132609zbMath1484.68181arXiv2001.07694OpenAlexW3001462218MaRDI QIDQ2127403
Peter Ashwin, Lorenzo Livi, Andrea Ceni, Claire M. Postlethwaite
Publication date: 20 April 2022
Published in: Physica D (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/2001.07694
recurrent neural networksmachine learningnonautonomous dynamical systemsmultistabilityinput-driven systemsecho state property
Learning and adaptive systems in artificial intelligence (68T05) Topological dynamics of nonautonomous systems (37B55) Networks and circuits as models of computation; circuit complexity (68Q06)
Related Items (3)
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reservoir computing approaches to recurrent neural network training
- Nonautonomous continuation of bounded solutions
- Random fixed point theorems with an application to random differential equations in Banach spaces
- Re-visiting the echo state property
- Echo state networks are universal
- Optimization and applications of echo state networks with leaky- integrator neurons
- Limitations of pullback attractors for processes
- Detection of generalized synchronization using echo state networks
- TOWARDS A MORSE THEORY FOR RANDOM DYNAMICAL SYSTEMS
- Forward attraction in nonautonomous difference equations
- A Geometrical Analysis of Global Stability in Trained Feedback Networks
- Morse Decomposition of Attractors for Non-autonomous Dynamical Systems
- Echo State Property Linked to an Input: Exploring a Fundamental Characteristic of Recurrent Neural Networks
This page was built for publication: The echo index and multistability in input-driven recurrent neural networks
