xwinxu/bayeSDE

Code for "Infinitely Deep Bayesian Neural Networks with Stochastic Differential Equations"

44
/ 100
Emerging

This is a specialized library for machine learning researchers and practitioners working with advanced neural network architectures. It helps in building and experimenting with neural networks that incorporate stochastic differential equations (SDEs) and Bayesian layers. Researchers can input their data and model specifications to explore how these 'infinitely deep' networks handle uncertainty and learn complex patterns in areas like image classification or regression.

174 stars. No commits in the last 6 months.

Use this if you are an AI/ML researcher or practitioner looking to implement and experiment with Bayesian Neural Networks based on Stochastic Differential Equations, particularly for tasks requiring robust uncertainty quantification or modeling complex, multimodal data distributions.

Not ideal if you are looking for a general-purpose machine learning library or a tool for standard neural network training without a specific focus on SDEs or Bayesian deep learning research.

deep-learning-research stochastic-modeling bayesian-inference neural-networks uncertainty-quantification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

174

Forks

28

Language

Python

License

MIT

Last pushed

Feb 11, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/xwinxu/bayeSDE"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.