Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.13967 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914836405813248 |
|---|---|
| author | Colusso, Paolo Filipović, Damir |
| author_facet | Colusso, Paolo Filipović, Damir |
| contents | We propose a function-learning methodology with a control-theoretical foundation. We parametrise the approximating function as the solution to a control system on a reproducing-kernel Hilbert space, and propose several methods to find the set of controls which bring the initial function as close as possible to the target function. At first, we derive the expression for the gradient of the cost function with respect to the controls that parametrise the difference equations. This allows us to find the optimal controls by means of gradient descent. In addition, we show how to compute derivatives of the approximating functions with respect to the controls and describe two optimisation methods relying on linear approximations of the approximating functions. We show how the assumptions we make lead to results which are coherent with Pontryagin's maximum principle. We test the optimisation methods on two toy examples and on two higher-dimensional real-world problems, showing that the approaches succeed in learning from real data and are versatile enough to tackle learning tasks of different nature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_13967 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Neural Control Systems Colusso, Paolo Filipović, Damir Optimization and Control We propose a function-learning methodology with a control-theoretical foundation. We parametrise the approximating function as the solution to a control system on a reproducing-kernel Hilbert space, and propose several methods to find the set of controls which bring the initial function as close as possible to the target function. At first, we derive the expression for the gradient of the cost function with respect to the controls that parametrise the difference equations. This allows us to find the optimal controls by means of gradient descent. In addition, we show how to compute derivatives of the approximating functions with respect to the controls and describe two optimisation methods relying on linear approximations of the approximating functions. We show how the assumptions we make lead to results which are coherent with Pontryagin's maximum principle. We test the optimisation methods on two toy examples and on two higher-dimensional real-world problems, showing that the approaches succeed in learning from real data and are versatile enough to tackle learning tasks of different nature. |
| title | Neural Control Systems |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2404.13967 |