Re-visiting the echo state property
From MaRDI portal
Publication:1942701
DOI10.1016/j.neunet.2012.07.005zbMath1258.68129OpenAlexW1989312953WikidataQ48412224 ScholiaQ48412224MaRDI QIDQ1942701
Stefan J. Kiebel, Herbert Jaeger, Izzet B. Yildiz
Publication date: 13 March 2013
Published in: Neural Networks (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.neunet.2012.07.005
Learning and adaptive systems in artificial intelligence (68T05) Neural networks for/in biological studies, artificial life and related topics (92B20) Applications of dynamical systems (37N99)
Related Items
The echo index and multistability in input-driven recurrent neural networks, Modelling and forecasting based on recursive incomplete pseudoinverse matrices, Unnamed Item, Detection of generalized synchronization using echo state networks, Echo state networks are universal, Prediction and identification of discrete-time dynamic nonlinear systems based on adaptive echo state network, Time series classification with echo memory networks, A decentralized training algorithm for echo state networks in distributed big data applications, A brain-inspired computational model for spatio-temporal information processing, Sensitivity -- local index to control chaoticity or gradient globally, Predicting shallow water dynamics using echo-state networks with transfer learning, Chaos may enhance expressivity in cerebellar granular layer, Robust optimization and validation of echo state networks for learning chaotic dynamics, Reservoir computing with error correction: long-term behaviors of stochastic dynamical systems, Seeking optimal parameters for achieving a lightweight reservoir computing: a computational endeavor, Input-Anticipating Critical Reservoirs Show Power Law Forgetting of Unexpected Input Events, Reservoir Computing with Computational Matter, Reservoir Computing with an Inertial Form, Stability and memory-loss go hand-in-hand: three results in dynamics and computation, Deep reservoir neural networks for trees, Unnamed Item, A new echo state network with variable memory length, Echo state networks trained by Tikhonov least squares are \(L^2(\mu)\) approximators of ergodic dynamical systems, Unnamed Item, On the Number of Circuits in Regular Matroids (with Connections to Lattices and Codes), Synchronization of reservoir computing models via a nonlinear controller, Memory and forecasting capacities of nonlinear recurrent networks
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Reservoir computing approaches to recurrent neural network training
- On discrete-time diagonal and \(D\)-stability
- The complex structured singular value
- Complex sensory-motor sequence learning based on recurrent state representation and reinforcement learning
- Optimization and applications of echo state networks with leaky- integrator neurons
- Connectivity, Dynamics, and Memory in Reservoir Computing with Binary and Analog Neurons
- Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations
- Real-Time Computation at the Edge of Chaos in Recurrent Neural Networks
- Global stability of a class of discrete-time recurrent neural networks
- Analysis and Design of Echo State Networks
- Elements of applied bifurcation theory
