https://github.com/daemon/neurde

Understanding neural differential equations, from theory to practice.
https://github.com/daemon/neurde

Last synced: 6 months ago
JSON representation

Understanding neural differential equations, from theory to practice.

• Host: GitHub
• URL: https://github.com/daemon/neurde
• Owner: daemon
• License: mit
• Created: 2023-04-01T01:01:28.000Z (about 3 years ago)
• Default Branch: main
• Last Pushed: 2023-04-02T05:54:59.000Z (about 3 years ago)
• Last Synced: 2025-02-04T13:43:48.240Z (over 1 year ago)
• Homepage:
• Size: 3.91 KB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# NeurDE

NeurDE (pronounced nɜrd) is a teaching library with Jupyter notebooks for understanding some of the neural differential equations literature, namely

1. [Neural Ordinary Differential Equations (2018)](https://arxiv.org/abs/1806.07366)

2. [Infinitely Deep Bayesian Neural Networks with SDEs (2021)](https://arxiv.org/abs/2102.06559)

For the engineering bits, the codebase is as cogent and comprehensive as possible, without any cryptic optimization tricks, to better facilitate learning.

As for the theoretical parts, the Jupyter notebooks contain a full dissection of neural ordinary differential equations (ODEs) and stochastic differential equations (SDEs).