The Future of Consumer Edge-AI Computing
Laskaridis, Stefanos, Venieris, Stylianos I., Kouris, Alexandros, Li, Rui, Lane, Nicholas D.
–arXiv.org Artificial Intelligence
In the last decade, Deep Learning has rapidly infiltrated the consumer end, mainly thanks to hardware acceleration across devices. However, as we look towards the future, it is evident that isolated hardware will be insufficient. Increasingly complex AI 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 reorganise and optimise 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.
arXiv.org Artificial Intelligence
Nov-7-2023
- Country:
- North America > United States
- District of Columbia > Washington (0.05)
- Virginia (0.04)
- California > Santa Clara County
- Palo Alto (0.04)
- Europe > United Kingdom
- England > Cambridgeshire > Cambridge (0.14)
- North America > United States
- Genre:
- Research Report (0.40)
- Industry:
- Information Technology > Security & Privacy (1.00)
- Energy (1.00)
- Telecommunications (0.68)
- Health & Medicine > Health Care Technology (0.68)
- Technology:
- Information Technology
- Security & Privacy (1.00)
- Communications > Networks (1.00)
- Cloud Computing (1.00)
- Hardware (0.94)
- Artificial Intelligence
- Natural Language (1.00)
- Machine Learning > Neural Networks
- Deep Learning (0.67)
- Information Technology