Uncertainty Quantification
Uncertainty quantification (UQ) in machine learning is the practice of measuring or estimating uncertainty in models. It is a set of tools to understand the limitations of models and predictions, and to make better decisions. UQ is a key component of trustworthy and interpretable machine learning.

Research feed

Pill

Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation

Identifying the source distribution behind observed data is an ill-posed problem. Sourcerer [Vet24S] introduces a novel approach based on …

Maternus Herold
Uncertainty Quantification
Seminar

Sampling Free Epistemic Uncertainty Through Approximated Variance Propagation

Noise injection methods such as dropout are popular ways of implicitly capturing epistemic uncertainty in neural networks. Usually, noise …

Faried Abu Zaid
Uncertainty Quantification
Seminar

Uncertainty quantification with conformal prediction

Conformal prediction is a method for uncertainty quantification that is based on the idea of conformal sets (CS). A CS is a set of …

Miguel de Benito Delgado
Uncertainty Quantification
Seminar

Robustly representing uncertainty through sampling in deep neural networks

In the previous instalments of our seminar series we have explored how bayesian methods can be used to estimate the epistemic uncertainty of …

Fabio Peruzzo
Uncertainty Quantification
Seminar

Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning

In this presentation, we revisit landmark research that interprets the dropout training process in deep neural networks as approximations of …

Iván Rodríguez
Uncertainty Quantification
Seminar

Aleatoric and epistemic uncertainty in machine learning

This talk introduces the notions of aleatoric and epistemic uncertainty for probabilistic models and gives an overview of recent …

Michael Panchenko
Uncertainty Quantification
Seminar

Monte Carlo-Dropout for Uncertainty Quantification in Deep Learning

Deep learning models are commonly used for regression tasks, producing a point estimate for a given set of inputs. However, a single point …

Maternus Herold
Uncertainty Quantification

Other series in Trustworthy and interpretable ML

Classifier calibration

For many applications of probabilistic classifiers it is important that the predicted confidence vectors reflect true probabilities (one …

Trustworthy and Interpretable ML

Simulation-Based Inference

Simulation-based inference (SBI) offers a powerful framework for Bayesian parameter estimation in intricate scientific simulations where …

Trustworthy and Interpretable ML

Probabilistic Models

Uncertainty permeates all aspects of real-world agency: Perception is subject to uncertainty owing to partial observability and unreliable …

Trustworthy and Interpretable ML

Explainable AI

Large opaque models like neural networks require dedicated methods to study and interpret their behavior. In this series we review recent …

Trustworthy and Interpretable ML
Check all of our work