Andreas Sideras
Researcher
Research Interests
Anomaly & Novelty Detection, Multimodal Machine Learning, Machine Learning in Low-Resource Scenarios
Contact
Additional Information
I completed my undergraduate studies in Computer Science & Engineering at the University of Ioannina and earned a Master’s degree in Artificial Intelligence through a joint program between NCSR Demokritos and the University of Piraeus (Department of Digital Systems). My MSc thesis is titled “Multimodal Pretraining for Music Audio.” Currently, I am pursuing a PhD in the Department of Digital Systems at the University of Piraeus, focusing on anomaly and novelty detection.
I have also worked as a machine learning and backend engineer in industry, and since 2022, I have been a research collaborator at NCSR Demokritos.
My research focuses on detecting anomalies and novelties in data, particularly when unexpected or unusual patterns arise. I am also interested in multimodal machine learning, which leverages diverse data types—such as text, tabular data, and time-series information—to improve performance. Additionally, I explore pretraining neural networks and applying machine learning techniques in low-resource scenarios, where data, ground truths, or computational resources are limited.