Top 18 uncertainty-quantification open source projects

[ICCV 2021 Oral] Deep Evidential Action Recognition

Bayesian deep convolutional encoder-decoder networks for surrogate modeling and uncertainty quantification

UQpy (Uncertainty Quantification with python) is a general purpose Python toolbox for modeling uncertainty in physical and mathematical systems.

High-performance framework for uncertainty quantification, optimization and reinforcement learning.

A library for uncertainty quantification based on PyTorch

Bayesian tools for fitting molecular mechanics torsion parameters to quantum chemical data.

Materials for STAT 991: Topics In Modern Statistical Learning (UPenn, 2022 Spring) - uncertainty quantification, conformal prediction, calibration, etc

Process global-scale satellite and airborne elevation data into time series of glacier mass change: Hugonnet et al. (2021).

Code for "Depth Uncertainty in Neural Networks" (https://arxiv.org/abs/2006.08437)

OpenCossan is an open and free toolbox for uncertainty quantification and management.

A professionally curated list of awesome Conformal Prediction videos, tutorials, books, papers, PhD and MSc theses, articles and open-source libraries.

Analysis of digital elevation models (DEMs)

Fast uncertainty quantification for scientific machine learning (SciML) and differential equations

Uncertainty-Wizard is a plugin on top of tensorflow.keras, allowing to easily and efficiently create uncertainty-aware deep neural networks. Also useful if you want to train multiple small models in parallel.

tools for scalable and non-intrusive parameter estimation, uncertainty analysis and sensitivity analysis

Using neural network to build expressive hierarchical distribution; A variational method to accurately estimate posterior uncertainty; A fast and general method for Bayesian inference. (ICML 2018)

(ICML 2022) Official PyTorch implementation of “Blurs Behave Like Ensembles: Spatial Smoothings to Improve Accuracy, Uncertainty, and Robustness”.

Uncertainty Quantification 360 (UQ360) is an extensible open-source toolkit that can help you estimate, communicate and use uncertainty in machine learning model predictions.