Συντάχθηκε 10-01-2024 12:29
Τόπος: Λ - Κτίριο Επιστημών/ΗΜΜΥ, 145Π-58
Έναρξη: 18/01/2024 12:00
Λήξη: 18/01/2024 13:00
Abstract
Predictive uncertainty estimation is valued as an important endeavor in various engineering disciplines. As this endeavor gains traction in the field of machine learning, it brings with it a series of fresh challenges that necessitate clear articulation and handling through formal means. This presentation provides a broad and holistic overview of concepts and methods for dealing with the most critical among such challenges. In particular, the overview addresses the following research questions:
- How can I estimate predictive uncertainty with machine learning?
- How can I maximize skill in predictive uncertainty estimation through machine learning?
The answers to these questions are supported by multiple examples of original research. These examples are devoted to engineering problems with diverse characteristics and technicalities, cover both temporal and spatial settings, and make use of big data and other large datasets from geoscience, remote sensing, and beyond.
About the Speaker
Georgia Papacharalampous holds a PhD in Engineering (2020) from the Department of Water Resources and Environmental Engineering of the National Technical University of Athens, Greece. During her time as a PhD candidate, she formulated and extensively compared a variety of methods for large-scale time series forecasting and statistical post-processing in geoscience by exploiting models and concepts from the machine learning, statistical, forecasting, and physics-based literature. For this research, she received the International Scientific Prize of the Dimitris N. Chorafas Foundation in the scientific area "Informatics and Computer Science." Her background also includes a Diploma in Civil Engineering (2014) and an MSc degree in Water Science and Technology (2016), both from the National Technical University of Athens, Greece. Her MSc degree was obtained from a program of postgraduate studies that runs under the collaboration of four schools, including the School of Civil Engineering and the School of Applied Mathematical and Physical Sciences.
Since the completion of her PhD, Georgia Papacharalampous has been focusing on several aspects of machine learning and time-series modelling in geoscience, remote sensing, and beyond in the frameworks of research projects. More precisely, she has completed her work at the Department of Civil Engineering of the University of Patras, Greece (2021), the Department of Engineering of the Roma Tre University, Italy (2021), and the Department of Water Resources and Environmental Modeling of the Faculty of Environmental Sciences of the Czech University of Life Sciences, Czech Republic (2022), and she currently works as a Principal Investigator - Postdoctoral Researcher at the School of Rural, Surveying, and Geoinformatics Engineering of the National Technical University of Athens, Greece.
Σύνδεσμος εκδήλωσης
