A General Constructive Upper Bound on Shallow Neural Nets Complexity
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911197120430080 |
|---|---|
| author | Hakl, Frantisek Fojtik, Vit |
| author_facet | Hakl, Frantisek Fojtik, Vit |
| contents | We provide an upper bound on the number of neurons required in a shallow
neural network to approximate a continuous function on a compact set with a
given accuracy. This method, inspired by a specific proof of the
Stone-Weierstrass theorem, is constructive and more general than previous
bounds of this character, as it applies to any continuous function on any
compact set. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06372 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | A General Constructive Upper Bound on Shallow Neural Nets Complexity Hakl, Frantisek Fojtik, Vit Machine Learning We provide an upper bound on the number of neurons required in a shallow neural network to approximate a continuous function on a compact set with a given accuracy. This method, inspired by a specific proof of the Stone-Weierstrass theorem, is constructive and more general than previous bounds of this character, as it applies to any continuous function on any compact set. |
| title | A General Constructive Upper Bound on Shallow Neural Nets Complexity |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2510.06372 |