Dimension of reservoir computers
From MaRDI portal
Abstract: A reservoir computer is a complex dynamical system, often created by coupling nonlinear nodes in a network. The nodes are all driven by a common driving signal. In this work, three dimension estimation methods, false nearest neighbor, covariance and Kaplan-Yorke dimensions, are used to estimate the dimension of the reservoir dynamical system. It is shown that the signals in the reservoir system exist on a relatively low dimensional surface. Changing the spectral radius of the reservoir network can increase the fractal dimension of the reservoir signals, leading to an increase in testing error.
Recommendations
- Low dimensional manifolds in reservoir computers
- On the characteristics and structures of dynamical systems suitable for reservoir computing
- Reservoir computing with an inertial form
- Path length statistics in reservoir computers
- Reducing network size and improving prediction stability of reservoir computing
Cites work
- Deterministic Nonperiodic Flow
- DISTRIBUTION OF EIGENVALUES FOR SOME SETS OF RANDOM MATRICES
- Ergodic theory of chaos and strange attractors
- scientific article; zbMATH DE number 711298 (Why is no real title available?)
- scientific article; zbMATH DE number 3100841 (Why is no real title available?)
- scientific article; zbMATH DE number 3111121 (Why is no real title available?)
- Hyperchaos of arbitrary order generated by a single feedback circuit, and the emergence of chaotic walks
- Measuring the strangeness of strange attractors
- Optimization and applications of echo state networks with leaky- integrator neurons
- Principal component analysis.
- Synchronization in chaotic systems
- Testing dynamical system variables for reconstruction
- The Lyapunov dimension of strange attractors
Cited in
(11)- Stability analysis of reservoir computers dynamics via Lyapunov functions
- Low dimensional manifolds in reservoir computers
- Symmetry kills the square in a multifunctional reservoir computer
- Reducing network size and improving prediction stability of reservoir computing
- Path length statistics in reservoir computers
- Reservoir Computing with Complex Cellular Automata
- Nonlinear memory capacity of parallel time-delay reservoir computers in the processing of multidimensional signals
- Reservoir computing with random and optimized time-shifts
- Complexity in subnetworks of a peroxidase-oxidase reaction model
- Decreased spinal inhibition leads to undiversified locomotor patterns
- Harnessing chaotic dynamics with optimized reservoir computer
This page was built for publication: Dimension of reservoir computers
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5218134)
