Abstract:
In the last decade, deep learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look toward the future, ...Show MoreMetadata
Abstract:
In the last decade, deep learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look toward the future, it is evident that isolated hardware will be insufficient. Increasingly complex artificial intelligence tasks demand shared resources, cross-device collaboration, and multiple data types, all without compromising user privacy or quality of experience. To address this, we introduce a novel paradigm centered around EdgeAI-Hub devices, designed to reorganize and optimize compute resources and data access at the consumer edge. To this end, we lay a holistic foundation for the transition from on-device to Edge-AI serving systems in consumer environments, detailing their components, structure, challenges, and opportunities.
Published in: IEEE Pervasive Computing ( Volume: 23, Issue: 3, July-Sept. 2024)