2 papers
cs.LG2024
Integrating uncertainty quantification into randomized smoothing based robustness guarantees
Sina Däubener, Kira Maag, David Krueger +1
Deep neural networks have proven to be extremely powerful, however, they are also vulnerable to adversarial attacks which can cause hazardous incorrect predictions in safety-critic…
cs.LG2020
Investigating maximum likelihood based training of infinite mixtures for uncertainty quantification
Sina Däubener, Asja Fischer
Uncertainty quantification in neural networks gained a lot of attention in the past years. The most popular approaches, Bayesian neural networks (BNNs), Monte Carlo dropout, and de…