PhD Seminar: Deep Generative Models for Anomaly Detection

Speaker: Artem Ryzhikov, third-year PhD student, Laboratory of Methods for Big Data Analysis, Faculty of Computer Science
Where: Zoom
When: February 9, 9:30–10:50 

Anomaly detection for complex data is a challenging task from the perspective of machine learning. This problem is characterized by a small number or absent anomalies in the training dataset, while significant statistics for the normal class are available. In this talk, we discuss a set of our studies on the application of deep generative models to anomaly detection on tabular, image, and time-series data.