orientino/dum-components
Code for "Training, Architecture, and Prior for Deterministic Uncertainty Methods" ICLR 2023 Workshop on Trustworthy ML
This project helps machine learning engineers and researchers build more reliable AI models. It provides methods and code to create models that not only make predictions but also estimate how confident they are in those predictions. This is particularly useful when dealing with new, unexpected data, allowing the model to flag when it's operating outside its comfort zone.
No commits in the last 6 months.
Use this if you are a machine learning practitioner developing models where understanding the certainty of predictions is critical, especially for identifying unusual or out-of-distribution data.
Not ideal if you are looking for a plug-and-play solution for simple prediction tasks without a strong need for uncertainty quantification or robust out-of-distribution detection.
Stars
12
Forks
1
Language
Python
License
MIT
Last pushed
Jun 15, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/orientino/dum-components"
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!