Harry24k/bayesian-neural-network-pytorch
PyTorch implementation of bayesian neural network [torchbnn]
This is a lightweight PyTorch implementation of a Bayesian neural network. It takes standard datasets for regression or classification (like the Iris dataset) and converts them into a Bayesian Neural Network, outputting models that include uncertainty estimates in their predictions. This is for machine learning practitioners or researchers who need to quantify the confidence of their model's output.
554 stars. No commits in the last 6 months.
Use this if you are a machine learning engineer working with PyTorch and need to add uncertainty estimation to your neural network models for regression or classification tasks.
Not ideal if you are not familiar with Python and PyTorch, or if you require a non-Bayesian deep learning solution.
Stars
554
Forks
87
Language
Python
License
MIT
Category
Last pushed
Jul 25, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Harry24k/bayesian-neural-network-pytorch"
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
thousandbrainsproject/tbp.monty
Monty is a sensorimotor learning framework based on the thousand brains theory of the neocortex.