aleximmer/Laplace
Laplace approximations for Deep Learning.
This project helps machine learning practitioners incorporate uncertainty directly into their deep learning models. By applying Laplace approximations to neural networks, it takes your trained model and training data to provide a refined model that can quantify its own prediction confidence. This is useful for data scientists, ML engineers, and researchers working with deep learning models.
535 stars. No commits in the last 6 months.
Use this if you need to understand the confidence or uncertainty in your deep learning model's predictions, rather than just getting a single output.
Not ideal if you're looking for a fully automated, 'set it and forget it' solution, as optimal results require experimentation with different configuration options.
Stars
535
Forks
89
Language
Python
License
MIT
Category
Last pushed
Apr 22, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aleximmer/Laplace"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
lululxvi/deepxde
A library for scientific machine learning and physics-informed learning
pnnl/neuromancer
Pytorch-based framework for solving parametric constrained optimization problems,...
wilsonrljr/sysidentpy
A Python Package For System Identification Using NARMAX Models
dynamicslab/pysindy
A package for the sparse identification of nonlinear dynamical systems from data
google-research/torchsde
Differentiable SDE solvers with GPU support and efficient sensitivity analysis.