Reducing echo state network size with controllability matrices
From MaRDI portal
Recommendations
- Echo state networks with filter neurons and a delay\&sum readout
- 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
- Re-visiting the echo state property
- A local echo state property through the largest Lyapunov exponent
Cites work
- scientific article; zbMATH DE number 1182386 (Why is no real title available?)
- Data-driven science and engineering. Machine learning, dynamical systems, and control
- Deep learning
- Dynamical systems as temporal feature spaces
- Echo state networks are universal
- Embedding and approximation theorems for echo state networks
- Existence and uniqueness of minimal realizations of nonlinear systems
- Forward accessibility for recurrent neural networks
- Good and bad predictions: assessing and improving the replication of chaotic attractors by means of reservoir computing
- On explaining the surprising success of reservoir computing forecaster of chaos? The universal machine learning dynamical system with contrast to VAR and DMD
- Re-visiting the echo state property
- Reducing network size and improving prediction stability of reservoir computing
- Robust forecasting using predictive generalized synchronization in reservoir computing
- Synchronization of reservoir computers with applications to communications
- The reservoir's perspective on generalized synchronization
- Using machine learning to replicate chaotic attractors and calculate Lyapunov exponents from data
This page was built for publication: Reducing echo state network size with controllability matrices
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6565128)
