Dimitrios Soudris

On-Sensor Printed Machine Learning Classification via Bespoke ADC and Decision Tree Co-Design

2024

Printed electronics (PE) technology provides cost-effective hardware with unmet customization, due to their low non-recurring engineering and fabrication costs. PE exhibit features such as flexibility, stretchability, porosity, and conformality, which make them a prominent candidate …

Towards Asynchronous Peer-to-Peer Federated Learning for Heterogeneous Systems

2025

Federated Learning (FL) enables collaborative model training across distributed, privacy-sensitive data sources. Traditional FL follows a centralized client-server architecture, relying on synchronized updates and uniform participation. However, real-world deployments face challenges such as client heterogeneity, …