2 citations · 2 across the 3 of their papers we have counts for
4 papers
Combining Statistical Features and Deep Encodings for Rehearsal-Based Class-Incremental Time Series Classification
Pablo GarcÃa-Santaclara, Bruno Fernández-Castro, Rebeca Pilar DÃaz-Redondo
Many systems used in real-world environments require adding new categories and incorporating new information without forgetting what was previously learnt by the classification mod…
Continual Learning for non-stationary regression via Memory-Efficient Replay
Pablo GarcÃa-Santaclara, Bruno Fernández-Castro, RebecaP. DÃaz-Redondo +1
Data streams are rarely static in dynamic environments like Industry 4.0. Instead, they constantly change, making traditional offline models outdated unless they can quickly adjust…
Continual Learning at the Edge: An Agnostic IIoT Architecture
Pablo GarcÃa-Santaclara, Bruno Fernández-Castro, Rebeca P. DÃaz-Redondo +2
The exponential growth of Internet-connected devices has presented challenges to traditional centralized computing systems due to latency and bandwidth limitations. Edge computing…
HLF-FSL. A Decentralized Federated Split Learning Solution for IoT on Hyperledger Fabric
Carlos Beis Penedo, Rebeca P. DÃaz Redondo, Ana Fernández Vilas +2
Collaborative machine learning in sensitive domains demands scalable, privacy preserving solutions for enterprise deployment. Conventional Federated Learning (FL) relies on a centr…