PhD Seminar • Machine Learning • Out-of-distribution Detection with Flow Generative Models
Please note: This PhD seminar will be given online.
Dihong Jiang, PhD candidate
David R. Cheriton School of Computer Science
Supervisor: Professor Yaoliang Yu
Out-of-distribution (OOD) data come from a distribution that is different from training data. Detecting OOD data contributes to secure deployment of machine learning models. Currently, deep generative models have been widely used as an unsupervised approach for OOD detection.