Uncertainty quantification for neural networks

In this seminar series, we review seminal and recent papers on uncertainty quantification that didn’t make it into our training on Bayesian ML.

All talks

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 injection is applied during training and inference. In the training phase, the networks learns to …

Faried Abu Zaid
Uncertainty Quantification

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 predictions that is guaranteed to contain the true value with a certain probability. This probability is …

Miguel de Benito Delgado
Uncertainty Quantification

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 a model, i.e. the uncertainty coming from the choice of network’s parameters. In particular, two …

Fabio Peruzzo
Uncertainty Quantification

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 Bayesian inference within deep Gaussian processes. As a direct outcome of this theoretical …

Iván Rodríguez
Uncertainty Quantification

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 developments in this area. It is mainly based on the corresponding review paper. Aleatoric uncertainty arises …

Michael Panchenko
Uncertainty Quantification

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 does not adequately reflect the model’s uncertainty about this estimate. In safety-critical …

Maternus Herold
Uncertainty Quantification