Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912256994836480 |
|---|---|
| author | Schoots, Nandi Villani, Mattia Jacopo de Bos, Niels uit |
| author_facet | Schoots, Nandi Villani, Mattia Jacopo de Bos, Niels uit |
| contents | Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (arXiv:2404.19756). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (univariate real) functions and ReLU networks. We provide completely explicit constructions to convert a piecewise linear KAN into a ReLU network and vice versa. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_01702 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks Schoots, Nandi Villani, Mattia Jacopo de Bos, Niels uit Machine Learning Artificial Intelligence Kolmogorov-Arnold Networks are a new family of neural network architectures which holds promise for overcoming the curse of dimensionality and has interpretability benefits (arXiv:2404.19756). In this paper, we explore the connection between Kolmogorov Arnold Networks (KANs) with piecewise linear (univariate real) functions and ReLU networks. We provide completely explicit constructions to convert a piecewise linear KAN into a ReLU network and vice versa. |
| title | Relating Piecewise Linear Kolmogorov Arnold Networks to ReLU Networks |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2503.01702 |