Saved in:
| Main Author: | |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2401.03965 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917561450364928 |
|---|---|
| author | Ruthotto, Lars |
| author_facet | Ruthotto, Lars |
| contents | This short, self-contained article seeks to introduce and survey continuous-time deep learning approaches that are based on neural ordinary differential equations (neural ODEs). It primarily targets readers familiar with ordinary and partial differential equations and their analysis who are curious to see their role in machine learning. Using three examples from machine learning and applied mathematics, we will see how neural ODEs can provide new insights into deep learning and a foundation for more efficient algorithms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_03965 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Differential Equations for Continuous-Time Deep Learning Ruthotto, Lars Machine Learning Dynamical Systems 97P80 (primary) 68T01, 68T07 (secondary) G.1.7; A.1 This short, self-contained article seeks to introduce and survey continuous-time deep learning approaches that are based on neural ordinary differential equations (neural ODEs). It primarily targets readers familiar with ordinary and partial differential equations and their analysis who are curious to see their role in machine learning. Using three examples from machine learning and applied mathematics, we will see how neural ODEs can provide new insights into deep learning and a foundation for more efficient algorithms. |
| title | Differential Equations for Continuous-Time Deep Learning |
| topic | Machine Learning Dynamical Systems 97P80 (primary) 68T01, 68T07 (secondary) G.1.7; A.1 |
| url | https://arxiv.org/abs/2401.03965 |