This repository contains my personal course notes and coding practices for Harvard's "CS50 Introduction to Artificial Intelligence with Python" course.

PyTorch implementation of Probabilistic MIMO U-Net

This repository provides the code used to implement the framework to provide deep learning models with total uncertainty estimates as described in "A General Framework for Uncertainty Estimation in Deep Learning" (Loquercio, Segù, Scaramuzza. RA-L 2020).

A library for Bayesian neural network layers and uncertainty estimation in Deep Learning extending the core of PyTorch

Official repository for the paper "Masksembles for Uncertainty Estimation" (CVPR 2021).

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

Code and supporting materials for the ICLR 2020 RIO paper

Simple and efficient way of performing deep ensembling to improve robustness as well as estimate uncertainty

Inferring distributions over depth from a single image, IROS 2019

Behaviour Cloning of Cartpole Swing-up Policy with Model-Predictive Uncertainty Regularization (UW CSE571 Guided Project)

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.

Model zoo for different kinds of uncertainty quantification methods used in Natural Language Processing, implemented in PyTorch.

NOMU: Neural Optimization-based Model Uncertainty

Code to accompany the paper 'Improving model calibration with accuracy versus uncertainty optimization'.

Uncertainty aware brain age prediction

A project to train your model from scratch or fine-tune a pretrained model using the losses provided in this library to improve out-of-distribution detection and uncertainty estimation performances. Calibrate your model to produce enhanced uncertainty estimations. Detect out-of-distribution data using the defined score type and threshold.

Wasserstein dropout (W-dropout) is a novel technique to quantify uncertainty in regression networks. It is fully non-parametric and yields accurate uncertainty estimates - even under data shifts.

Official Code: Trust Your Robots! Predictive Uncertainty Estimation of Neural Networks with Sparse Gaussian Processes

[WACV'22] Official implementation of "HHP-Net: A light Heteroscedastic neural network for Head Pose estimation with uncertainty"

This repository provides the official implementation of "Robust channel-wise illumination estimation." accepted in BMVC (2021).