Two-step counterfactual generation for OOD examples
N Keshtmand, R Santos-Rodriguez, J Lawry - arXiv preprint arXiv …, 2023 - arxiv.org
Two fundamental requirements for the deployment of machine learning models in safety-
critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be …
critical systems are to be able to detect out-of-distribution (OOD) data correctly and to be …
Bayesian Neural Networks for Out of Distribution Detection
JI Mitros - 2022 - researchrepository.ucd.ie
Empirical studies have demonstrated that point estimate deep neural networks despite
being expressive estimators capturing rich interactions between covariates, nevertheless …
being expressive estimators capturing rich interactions between covariates, nevertheless …
Evaluating, Explaining, and Utilizing Model Uncertainty in High-Performing, Opaque Machine Learning Models
KE Brown - 2023 - search.proquest.com
Machine learning has made tremendous strides in the past decades at producing state-of-
the-art results in safety-critical fields such as self-driving vehicles and medicine. Current …
the-art results in safety-critical fields such as self-driving vehicles and medicine. Current …