cambridge-mlg/DUN
Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)
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.
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.
Higher-rated alternatives
EmuKit/emukit
A Python-based toolbox of various methods in decision making, uncertainty quantification and...
google/uncertainty-baselines
High-quality implementations of standard and SOTA methods on a variety of tasks.
nielstron/quantulum3
Library for unit extraction - fork of quantulum for python3
IBM/UQ360
Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you...
aamini/evidential-deep-learning
Learn fast, scalable, and calibrated measures of uncertainty using neural networks!