anassinator/bnn
Bayesian Neural Network in PyTorch
This project helps machine learning practitioners build models that not only make predictions but also quantify how confident those predictions are. You input your dataset, and it provides a neural network model that outputs predictions along with a measure of their uncertainty. This is valuable for data scientists, machine learning engineers, and researchers who need to understand the reliability of their models.
No commits in the last 6 months.
Use this if you need to understand the uncertainty or confidence in your machine learning model's predictions, rather than just getting a single prediction value.
Not ideal if you are looking for a simple, off-the-shelf neural network for basic prediction tasks where uncertainty quantification is not a primary concern.
Stars
93
Forks
27
Language
Python
License
MIT
Category
Last pushed
May 03, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/anassinator/bnn"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
sbi-dev/sbi
sbi is a Python package for simulation-based inference, designed to meet the needs of both...
SMTorg/smt
Surrogate Modeling Toolbox
reservoirpy/reservoirpy
A simple and flexible code for Reservoir Computing architectures like Echo State Networks
GPflow/GPflow
Gaussian processes in TensorFlow
dswah/pyGAM
[CONTRIBUTORS WELCOME] Generalized Additive Models in Python