Alvaro is a 24-year-old researcher specializing in Federated Learning, a novel approach that enables collaborative artificial intelligence model development across institutions constrained by data protection regulations. In this paradigm, each institution trains a local model on its private data, which is then securely transmitted to a federated server. The server aggregates these models into a global model that incorporates knowledge from all participating datasets while preserving the privacy of the original data sources. This global model is subsequently redistributed to the institutions for further local refinement, initiating an iterative process that continues until convergence is achieved and a robust model is produced.
His current research, conducted in collaboration between the AI Lab and the AIMS initiative, focuses on applying Federated Learning in the healthcare sector. The aim is to develop more accurate early detection models for neurological diseases such as Alzheimer’s disease and Multiple Sclerosis. By leveraging data from multiple hospitals—each of which holds a limited number of MRI scans—this approach seeks to overcome data scarcity while ensuring compliance with the General Data Protection Regulation (GDPR).