| KEYWORD |
Sustainable AI via Distributed Transfer Learning over Edge Networks
Thesis abroad
Reference persons GUIDO MARCHETTO, ALESSIO SACCO
External reference persons Prof. Flavio Esposito - St. Louis University, USA
Research Groups DAUIN - GR-03 - COMPUTER NETWORKS GROUP - NETGROUP
Description Transfer learning does not train from scratch but leverages existing models to help train the new model for better accuracy. Unfortunately, realizing transfer learning in distributed cloud-edge networks faces critical challenges such as online training, uncertain network environments, time-coupled control decisions, and the balance between resource consumption and model accuracy. In this project, students will design, implement, and evaluate solutions for sustainable distributed machine learning using transfer learning techniques, sharing our lesson learned in a scientific publication.
Deadline 08/02/2025
PROPONI LA TUA CANDIDATURA