JavierAntoran/Bayesian-Neural-Networks
Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more
This project offers various approaches for building neural networks that can quantify their own uncertainty. You provide your dataset, and it outputs a model that not only makes predictions but also indicates how confident it is in those predictions. This is for machine learning practitioners or researchers who need to understand the reliability of their models.
1,960 stars. No commits in the last 6 months.
Use this if you are developing machine learning models and need to understand the confidence or potential errors associated with your predictions, rather than just getting a single output.
Not ideal if you are looking for a simple, 'black-box' prediction model without needing to interpret the uncertainty of its outputs.
Stars
1,960
Forks
305
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Oct 20, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JavierAntoran/Bayesian-Neural-Networks"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
tensorflow/probability
Probabilistic reasoning and statistical analysis in TensorFlow
pyro-ppl/pyro
Deep universal probabilistic programming with Python and PyTorch
erdogant/bnlearn
Python package for Causal Discovery by learning the graphical structure of Bayesian networks....
probml/pyprobml
Python code for "Probabilistic Machine learning" book by Kevin Murphy
google/edward2
A simple probabilistic programming language.