Serdecznie zapraszamy na seminarium Wydziału Informatyki AGH, które odbędzie się 13 czerwca 2024 r. (tj. czwartek) od godz. 12:00 do 13:00 w sali 2.41.
Gościem najbliższego spotkania będzie dr Roberto Corizzo z American University w Waszyngtonie, który przedstawi seminarium o tytule “Lifelong Continual Learning: A New Perspective for Anomaly Detection”.
Tematyka seminarium:
Anomaly detection is of paramount importance in many real-world domains characterized by evolving behavior, such as monitoring cyber-physical systems, human conditions and network traffic. Current research in anomaly detection leverages offline learning working with static data or online learning focusing on constant adaptation to evolving data. At the same time, lifelong learning represents an emerging trend, answering the need for machine learning models that continuously adapt to new challenges in dynamic environments while retaining past knowledge. Although this aspect could be beneficial to build effective and robust anomaly detection models, lifelong learning research is mainly dedicated to proposing new model update strategies in image classification and reinforcement learning domains.
This seminar will showcase the adoption of lifelong anomaly detection as a relevant research approach to designing more robust models that provide a comprehensive view of the environment, as well as simultaneous adaptation and knowledge retention. After a brief introduction on lifelong/continual learning, its intersection with anomaly detection will be covered, introducing scenarios, strategies, and metrics. A scenario extraction procedure, which enables researchers to experiment with lifelong anomaly detection using any existing dataset, will be introduced. Following up, recently obtained results with benchmark anomaly detection datasets will be discussed, emphasizing the gap in performance that could be filled with the adoption of lifelong/continual learning. The focus will then shift to concept-agnostic learning and change detection as a viable way to detect transitions between concepts. To wrap up, current research gaps and avenues for future research will be emphasized.
BIO prelegenta:
Roberto Corizzo received the Ph.D. degree in computer science from the University of Bari Aldo Moro, Bari, Italy, in 2018. He was a Research Fellow with the Department of Computer Science, University of Bari, Bari. He is currently an Assistant Professor with the Department of Computer Science, American University, Washington, DC, USA.
He conducts research on spatio-temporal data mining, big data analytics, and continual learning. His research addresses analytical tasks such as sensor data forecasting, time series classification, predictive modeling, and feature extraction tailored to real-world applications in fields such as energy, cybersecurity, astrophysics, and social networks.
He has coauthored over 50 articles, including 15 publications in journals, such as IEEE Transactions on Industrial Informatics, Neural Networks, and Machine Learning. Dr. Corizzo participated in the scientific committee of international conferences and served as a reviewer for several international journals.
Dane do połączenia zdalnego:
https://agh-mche.webex.com/meet/informatyka
Meeting Number: 137 373 4650
Join by video system - dial: informatyka@agh-mche.webex.com