5 papers
Fully-sensorized smart-eyewear platform for on-device Machine Learning
Andrea Giudici, Christian Veronesi, Pietro Bartoli +5
This paper presents ARGO, a smart eyewear platform designed to bridge ergonomic comfort, high computational throughput, and energy efficiency. Unlike cloud-dependent solutions, ARG…
Federated Reinforcement Learning for Runtime Optimization of AI Applications in Smart Eyewears
Hamta Sedghani, Abednego Wamuhindo Kambale, Federica Filippini +3
Extended reality technologies are transforming fields such as healthcare, entertainment, and education, with Smart Eye-Wears (SEWs) and Artificial Intelligence (AI) playing a cruci…
DQT: Dynamic Quantization Training via Dequantization-Free Nested Integer Arithmetic
Hazem Hesham Yousef Shalby, Fabrizio Pittorino, Francesca Palermo +2
The deployment of deep neural networks on resource-constrained devices relies on quantization. While static, uniform quantization applies a fixed bit-width to all inputs, it fails…
Benchmarking Energy and Latency in TinyML: A Novel Method for Resource-Constrained AI
Pietro Bartoli, Christian Veronesi, Andrea Giudici +3
The rise of IoT has increased the need for on-edge machine learning, with TinyML emerging as a promising solution for resource-constrained devices such as MCU. However, evaluating…
On-Sensor Convolutional Neural Networks with Early-Exits
Hazem Hesham Yousef Shalby, Arianna De Vecchi, Alice Scandelli +4
Tiny Machine Learning (TinyML) is a novel research field aiming at integrating Machine Learning (ML) within embedded devices with limited memory, computation, and energy. Recently,…