Dynamic learning based on random recurrent neural networks and reservoir computing systems |
Dr. Lukas GONON, Universität St. Gallen |
Thursday, 2019-11-07 18:00 |
|
In this talk we present our recent results on a mathematical explanation for the empirical success of dynamic learning based on reservoir computing. Motivated by their performance in applications ranging from realized volatility forecasting to chaotic dynamical systems, we study approximation and learning based on random recurrent neural networks and more general reservoir computing systems. For different types of echo state networks we obtain high-probability bounds on the approximation error in terms of the network parameters. For a more general class of reservoir computing systems and weakly dependent (possibly non-i.i.d.) input data, we then also derive generalization error bounds based on a Rademacher-type complexity. The talk is based on joint work with Lyudmila Grigoryeva and Juan-Pablo Ortega. |