Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914607624355840 |
|---|---|
| author | Yu, Tianchi Qiu, Jingwei Yang, Jiang Oseledets, Ivan |
| author_facet | Yu, Tianchi Qiu, Jingwei Yang, Jiang Oseledets, Ivan |
| contents | In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation functions, which recently gained attention as alternatives to Multilayer Perceptron. Many different function representations have already been tried, but we show that Sinc interpolation proposes a viable alternative, since it is known in numerical analysis to effectively represent both smooth functions and functions with singularities. This is important not only for function approximation but also for solving the partial differential equations with physics-informed neural networks. Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_04096 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities Yu, Tianchi Qiu, Jingwei Yang, Jiang Oseledets, Ivan Machine Learning Artificial Intelligence Numerical Analysis Neural and Evolutionary Computing Computational Physics In this paper, we propose to use Sinc interpolation in the context of Kolmogorov-Arnold Networks, neural networks with learnable activation functions, which recently gained attention as alternatives to Multilayer Perceptron. Many different function representations have already been tried, but we show that Sinc interpolation proposes a viable alternative, since it is known in numerical analysis to effectively represent both smooth functions and functions with singularities. This is important not only for function approximation but also for solving the partial differential equations with physics-informed neural networks. Through a series of experiments, we show that SincKANs provide better results in almost all of the examples we have considered. |
| title | Sinc Kolmogorov-Arnold network and its application for solving PDEs with singularities |
| topic | Machine Learning Artificial Intelligence Numerical Analysis Neural and Evolutionary Computing Computational Physics |
| url | https://arxiv.org/abs/2410.04096 |