matthewachan/hyperdm

Official repository for "Estimating Epistemic and Aleatoric Uncertainty with a Single Model"

36
/ 100
Emerging

This project helps scientists and practitioners using machine learning in high-stakes fields like medical imaging and weather forecasting to understand the reliability of their model predictions. It takes a trained machine learning model and provides two types of uncertainty estimates: epistemic (reducible with more data) and aleatoric (inherent to the task). This allows users to make more informed decisions about when to trust a model's output.

No commits in the last 6 months.

Use this if you need to precisely quantify and disentangle different types of uncertainty in your machine learning predictions for critical applications without the computational cost of training many separate models.

Not ideal if your application does not require detailed uncertainty quantification or if you are working with simpler models where traditional ensemble methods are already computationally feasible.

medical-imaging weather-forecasting risk-assessment predictive-modeling scientific-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

23

Forks

4

Language

Python

License

GPL-3.0

Last pushed

Nov 07, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/matthewachan/hyperdm"

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