cambridge-mlg/DUN

Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)

39
/ 100
Emerging

This project offers a method for training deep learning models that can estimate their own prediction uncertainty efficiently. It takes in various types of data, like numerical tables or images, and produces predictions along with a measure of how confident the model is in those predictions. This is particularly useful for machine learning engineers or researchers who need reliable uncertainty estimates without high computational costs.

No commits in the last 6 months.

Use this if you are building deep learning models for regression or image classification and need to understand the reliability of your model's predictions with a single pass, especially when computational resources are limited.

Not ideal if your primary goal is to simply make predictions without needing uncertainty quantification, or if you have ample computational resources to use more complex ensemble methods.

predictive-modeling model-robustness machine-learning-engineering uncertainty-quantification image-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

78

Forks

11

Language

Jupyter Notebook

License

MIT

Last pushed

Oct 03, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/cambridge-mlg/DUN"

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