Abstract: Most deep learning models assume ideal conditions and rely on the assumption that test/production data comes from the in-distribution samples from the training data. However, this assumption is not satisfied in most real-world applications. Test data could differ from the training data either due to adversarial perturbations, new classes, generated content, noise, or other distribution changes. These shifts in the input data can lead to classifying unknown types, classes that do not appear during training, as known with high confidence. On the other hand, adversarial perturbations in the input data can cause a sample to be incorrectly classified. In this talk,  we will discuss approaches based on group-based and individual subset scanning methods from the anomalous pattern detection domain and how they can be applied over off-the-shelf deep learning models.

Biography: Celia Cintas is a Research Scientist at IBM Research Africa - Nairobi. She is a member of the AI Science team at the Kenya Lab. Her current research explores subset scanning for anomalous pattern detection under generative models and the study of robustness and fairness in machine learning. Previously, a grantee from the National Scientific and Technical Research Council at LCI-UNS and IPCSH-CONICET. She holds a Ph.D. in Computer Science from Universidad del Sur (Argentina). More details at https://celiacintas.io/  

This talk is part of the SLT CDT's Responsible Research and Innovation (RRI) Talk Series.