Abstract
Few-Shot Class-Incremental Learning (FSCIL) enables machine learning systems to expand their inference capabilities to new classes using only a few labeled examples, without forgetting previously learned classes. Classical backpropagation-based learning is often unsuitable for battery-powered, memory-constrained systems at the extreme edge; this work introduces an online FSCIL approach that learns new classes on-device at a cost of 12 mJ per class.
Type
Thorir Mar Ingolfsson
Postdoctoral Researcher
I develop efficient machine learning systems for biomedical wearables that operate under extreme resource constraints. My work bridges foundation models, neural architecture design, and edge deployment to enable real-time biosignal analysis on microwatt-scale devices.