| dc.rights.license | CC-BY-NC-ND | |
| dc.contributor.advisor | Dirksen, S. | |
| dc.contributor.author | Grovenstein, Yora | |
| dc.date.accessioned | 2025-08-12T14:00:54Z | |
| dc.date.available | 2025-08-12T14:00:54Z | |
| dc.date.issued | 2025 | |
| dc.identifier.uri | https://studenttheses.uu.nl/handle/20.500.12932/49687 | |
| dc.description.abstract | The thesis introduces an algorithm that constructs a three-layer neural network in polynomial time. It is proven that under the threshold activation function the size of the constructed neural network depends only on the geometric relationship between the two classes, rather than the size of the dataset. | |
| dc.description.sponsorship | Utrecht University | |
| dc.language.iso | EN | |
| dc.subject | The thesis introduces an algorithm that constructs a three-layer neural network in polynomial time. It is proven that under the threshold activation function the size of the constructed neural network depends only on the geometric relationship between the two classes, rather than the size of the dataset. | |
| dc.title | Interpolating Neural Network Construction Independent of Dataset Size | |
| dc.type.content | Bachelor Thesis | |
| dc.rights.accessrights | Open Access | |
| dc.subject.courseuu | Wiskunde & Toepassingen | |
| dc.thesis.id | 51425 | |
