University of South Florida
Data-Driven Learning Algorithm Via Densely-Defined Multiplication Operators and Occupation Kernels.
Abstract
dc:descriptionConsider a nonautonomous nonlinear evolution \dot{x}=f(x,t,μ), where the vector x(t) \in \mathbb{R}n represents the state of the dynamical system at time $t$, μ contains system parameters, and $f(\cdot)$ represents a dynamic constraint. In most practical applications, the nonlinear dynamic constraint $f$ is unknown analytically. The problem of approximating $f$ directly from data measurements generated by the system is a main goal of this manuscript. In the postulates of the Nonlinear Autoregressive (NAR) framework, we show that the problem of approximating $f$ can be studied through symbols of densely defined multiplication operators over a Reproducing Kernel Hilbert Spaces (RKHS). In this formulation, data is mapped into a RKHS by virtue of occupation kernels which are special functions that reside in a RKHS owing to an integration functional. The resulting scheme is a parameter identification algorithm where system parameters are approximated according to some induced structure on the symbols of the operator. The action of the adjoint multiplication on an occupation kernel induces a kernelized transform which is the subject of study in the second part of the dissertation.
Degree
thesis:*- Name thesis:degree_name
- Doctor of Philosophy (Ph.D.)
- Level thesis:degree_level
- Dissertation
- Discipline thesis:degree_discipline
- Mathematics and Statistics
- Grantor
- University of South Florida
- Year dc:date
- 2023
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Kyei, John
- Contributors dc:contributor
-
- Razvan Teodorescu, Ph.D.
- Joel A. Rosendfeld, Ph.D.
- Catherine A. Beneteau, Ph.D.
- Dmitry Khavinson, Ph.D.
- Benjamin P. Russo, Ph.D.
Subjects
dc:subject × 6Identifiers
dc:identifier.*- Repository record dc:identifier
- https://digitalcommons.usf.edu/etd/10440