piEsposito/blitz-bayesian-deep-learning
A PyTorch library providing Bayesian neural network layers with weight uncertainty for regression and classification.
Not currently ranked — collecting fresh signals.
star history
BLiTZ is a Python library that extends PyTorch with Bayesian neural network layers implementing weight uncertainty as described in the seminal paper on Weight Uncertainty in Neural Networks. It provides variational layers where weights are sampled from learned distributions rather than fixed values, enabling uncertainty quantification in deep learning models. The library integrates seamlessly with standard PyTorch workflows, allowing users to add probabilistic modeling capabilities to existing architectures while maintaining compatibility with standard layers and training loops.
Frequently asked
- What is piEsposito/blitz-bayesian-deep-learning?
- A PyTorch library providing Bayesian neural network layers with weight uncertainty for regression and classification.
- Is blitz-bayesian-deep-learning open source?
- Yes — piEsposito/blitz-bayesian-deep-learning is open source, released under the GPL-3.0 license.
- What language is blitz-bayesian-deep-learning written in?
- piEsposito/blitz-bayesian-deep-learning is primarily written in Python.
- How popular is blitz-bayesian-deep-learning?
- piEsposito/blitz-bayesian-deep-learning has 983 stars on GitHub.
- Where can I find blitz-bayesian-deep-learning?
- piEsposito/blitz-bayesian-deep-learning is on GitHub at https://github.com/piEsposito/blitz-bayesian-deep-learning.