Talk by Prof. Marius Kloft: "Deep Anomaly Detection"

  • Venue:

    Karlsruher Decision and Design Laboratory (KD2Lab)

  • Date:

    9 December 2022 - 10:30

  • Speaker:

    Prof. Dr. Marius Kloft, Professor of Machine Learning, University of Kaiserslautern

     

    Marius Kloft has worked and researched at various institutions in Germany and the US, including TU Berlin (PhD), UC Berkeley (PhD), New York University (Postdoc), Memorial Sloan-Kettering Cancer Center New York (Postdoc), HU Berlin (Jun.-Prof.), and USC Los Angeles (Assoc. Prof.). Since 2017 he is a professor of machine learning at TU Kaiserslautern. His research covers a broad spectrum of machine learning, from mathematical theory and fundamental algorithms to applications in chemical and mechanical engineering. He received the Google Most Influential Papers 2013 Award, and is an alumni of DFG's Emmy-Noether program. He is the spokesperson of the DFG research group FOR 5359 and a co-organizer of the DFG SPPs 2331 and 2364.
    On this occation, he will talk about 'deep anomaly detection' - a field where he took a significant role in creating and establishing. The key question in anomaly detection is: Which data instances deviate from the norm? This question drives humankind since thousands of years. Once again, it has come into spotlight due to revolutionary breakthroughs in computing technology and modern artificial intelligence based on deep learning.

     

    In 2022, the paper 'Deep One-class Classification' main-authored by Marius Kloft received the ANDEA Test-of-Time Award for the most influential paper in anomaly detection in the last ten years (2012-2022). The paper is highly cited, with more than 400 annual citations.

  • Abstract:

    Anomaly detection is one of the fundamental topics in machine learning and artificial intelligence. The aim is to find instances deviating from the norm - so-called 'anomalies'. Anomalies are absolutely everywhere, from attacks on computer or energy networks to critical faults in a chemical factory or rare tumors in cancer imaging data. In my talk, I will first introduce the field of anomaly detection, with an emphasis on 'deep anomaly detection' (anomaly detection based on deep learning). Then, I will present recent algorithms for deep anomaly detection, with images as primary data type. I will demonstrate how these methods can be better understood using explainable AI methods. I will show new algorithms for deep anomaly detection on other data types, such as time series, graphs, tabular data, and contamined data. Finally, I will close my talk with an outlook on exciting future research directions in anomaly detection and beyond.

  • Place:

    Fritz-Erler-Straße 1-3 (Zähringer-Haus), Bldg.01.85

  • Links: