borchero/natural-posterior-network

Official Implementation of "Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions" (ICLR, 2022)

42
/ 100
Emerging

This project offers a Python implementation for researchers and machine learning practitioners to build deep learning models that not only make predictions but also quantify their uncertainty. It takes in various datasets and produces models that provide both predictions and a measure of confidence for those predictions. This is for users who need to understand 'how sure' their model is about its outputs, especially in critical applications.

No commits in the last 6 months.

Use this if you need to integrate robust uncertainty quantification directly into your deep learning models for predictive tasks.

Not ideal if you are looking for a simple predictive model without the need for detailed uncertainty estimates.

predictive-modeling machine-learning-research deep-learning-applications uncertainty-quantification bayesian-inference
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

87

Forks

16

Language

Python

License

MIT

Last pushed

Apr 05, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/borchero/natural-posterior-network"

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