On the stability properties of gated recurrent units neural networks
The paper provides sufficient sufficient conditions for input-to-state stability (ISS) and the incremental input-to-state stability (\(\delta\)ISS) of gated recurrent units (GRUs) neural networks. Both single-layer architecture \[ \begin{cases} x^+ = z \circ x + (1-z) \circ \phi(W_r u + U_r f \circ x + b_r)\\ z = \sigma(W_z u + U_z x + b_z)\\ f = \sigma(W_f u + U_f x + b_f)\\ y = U_0 x + b_0 \end{cases}, \] and its multi-layer counterpart are considered. Here \(x\in\mathbb R^{n_x}\), \(n_x \in \mathbb N\) is the state vector, \(u\in \mathbb R^{n_u}\), \(n_u \in \mathbb N\) is the input vector, \(y \in \mathbb R^{n_o}\), \(n_o \in \mathbb N\) is the output vector. The matrices \(W_*\), \(U_*\), and \(b_*\) are the weights and biases that parametrize the model. The derived sufficient stability conditions consist of nonlinear inequalities on the network's weights. They can be utilized in various ways, e.g., to verify stability of the trained network, or they can be enforced as constraints during the training procedure of a GRU. The resulting training procedure is tested on a quadruple tank nonlinear benchmark system.
- Stability of gated recurrent unit neural networks: convex combination formulation approach
- Stability of multilayer recursive neural networks
- Stability, robustness and approximation properties of gradient recurrent high‐order neural networks
- Stability of two-layer recursive neural networks
- Improved asymptotical stability criteria for static recurrent neural networks
- Stability of discrete time recurrent neural networks and nonlinear optimization problems
- A Lyapunov approach to incremental stability properties
- Deep learning
- Global asymptotic stability and stabilization of long short-term memory neural networks with constant weights and biases
- Input-to-state stability for discrete-time nonlinear systems
- Moving-horizon state estimation for nonlinear discrete-time systems: new stability results and approximation schemes
- Multilayer feedforward networks are universal approximators
- Neural networks for control systems - a survey
- Recurrent neural network-based model predictive control for continuous pharmaceutical manufacturing
- Stability of gated recurrent unit neural networks: convex combination formulation approach
- Recurrent neural network-based internal model control design for stable nonlinear systems
- Robust constrained nonlinear model predictive control with gated recurrent unit model
- Robust offset‐free nonlinear model predictive control for systems learned by neural nonlinear autoregressive exogenous models
- Nonlinear MPC design for incrementally ISS systems with application to GRU networks
- Deep networks for system identification: a survey
- Regional stability conditions for recurrent neural network-based control systems
- On incremental input-to-state stability of interconnected discrete-time systems
- Data-driven control of echo state-based recurrent neural networks with robust stability guarantees
- Reduced-order echo state networks for model predictive control in industrial applications
This page was built for publication: On the stability properties of gated recurrent units neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2059489)
