kyle-dorman/bayesian-neural-network-blogpost
Building a Bayesian deep learning classifier
This project guides machine learning practitioners on building a deep learning classifier that can assess its own confidence in predictions. It takes in image datasets, like those used for object recognition, and outputs classification predictions along with measures of uncertainty. Data scientists and machine learning engineers can use this to build more robust and reliable AI systems.
491 stars. No commits in the last 6 months.
Use this if you need your image classification models to not only make predictions but also tell you when they are unsure, which is crucial for applications where errors have significant consequences.
Not ideal if you are looking for a pre-built, production-ready solution, as this project serves as an educational guide for implementing Bayesian deep learning concepts.
Stars
491
Forks
104
Language
Jupyter Notebook
License
—
Category
Last pushed
Oct 30, 2017
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kyle-dorman/bayesian-neural-network-blogpost"
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.