On Efficient Training & Inference of Neural Differential Equations
The democratization of machine learning requires architectures that automatically adapt to new problems. Neural Differential Equations have emerged as a popular modeling framework, enabling ML practitioners to design neural networks that can adaptively modify their depth based on the input problem....
| Main Author: | |
|---|---|
| Other Authors: | |
| Format: | Thesis |
| Published: |
Massachusetts Institute of Technology
2023
|
| Online Access: | https://hdl.handle.net/1721.1/151379 |