Universal approximation power of deep residual neural networks via nonlinear control theory.
Paulo TabuadaBahman GharesifardPublished in: ICLR (2021)
Keyphrases
- control theory
- neural network
- variable structure
- linear systems
- dynamical systems
- control law
- artificial neural networks
- fuzzy logic
- back propagation
- fuzzy systems
- adaptive neural
- feed forward
- differential equations
- communication delays
- neural model
- neural network model
- dynamic environments
- genetic algorithm
- closed loop
- nonlinear functions
- radial basis function
- high order
- real time