Time series forecasting with PyTorch

Pytorch implementations of Bayes By Backprop, MC Dropout, SGLD, the Local Reparametrization Trick, KF-Laplace, SG-HMC and more

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

A Library for Uncertainty Quantification.

Sensitivity Analysis Library in Python. Contains Sobol, Morris, FAST, and other methods.

Visualizations of distributions and uncertainty

Lightweight, useful implementation of conformal prediction on real data.

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

Learn fast, scalable, and calibrated measures of uncertainty using neural networks!

This repo contains a PyTorch implementation of the paper: "Evidential Deep Learning to Quantify Classification Uncertainty"

A 3D vision library from 2D keypoints: monocular and stereo 3D detection for humans, social distancing, and body orientation.

A state-of-the-art distributed system using Reactive DDD as uncertainty modeling, Event Storming as subdomain decomposition, Event Sourcing as an eventual persistence mechanism, CQRS, Async Projections, Microservices for individual deployable units, Event-driven Architecture for efficient integration, and Clean Architecture as domain-centric design

Asynchronous Multiple LiDAR-Inertial Odometry using Point-wise Inter-LiDAR Uncertainty Propagation

A curated list of trustworthy deep learning papers. Daily updating...

(ICCV 2019) Uncertainty-aware Face Representation and Recognition

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

Self-Supervised Learning for OOD Detection (NeurIPS 2019)

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

The DESPOT online POMDP solver

Wrapper for a PyTorch classifier which allows it to output prediction sets. The sets are theoretically guaranteed to contain the true class with high probability (via conformal prediction).