borchero/natural-posterior-network
Official Implementation of "Natural Posterior Network: Deep Bayesian Predictive Uncertainty for Exponential Family Distributions" (ICLR, 2022)
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.
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.
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!