activatedgeek/understanding-bayesian-classification
On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification
This project helps machine learning researchers improve the reliability and accuracy of their classification models, especially when dealing with noisy or uncertain data. It takes in existing classification datasets and models, and by accounting for data randomness, it outputs models with better performance and more robust uncertainty estimates. It's for researchers and practitioners building and evaluating advanced classification systems.
No commits in the last 6 months.
Use this if you are developing or researching Bayesian neural networks for classification and need to improve model performance and uncertainty quantification, particularly when your data has inherent noise or ambiguity.
Not ideal if you are looking for an out-of-the-box solution for standard classification tasks without delving into the theoretical underpinnings of Bayesian methods or model likelihoods.
Stars
21
Forks
1
Language
Jupyter Notebook
License
Apache-2.0
Last pushed
Apr 01, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/activatedgeek/understanding-bayesian-classification"
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!