<p>➀ Researchers from TU Graz, Pro2Future, and the University of St. Gallen developed methods to deploy AI models on resource-constrained IoT devices with as little as 4KB memory, enabling localized processing without external compute resources; </p><p>➁ The team used techniques like model partitioning, Subspace-Configurable Networks (SCNs), quantization, and pruning to balance model size and accuracy, achieving up to 7.8x faster image processing on IoT devices; </p><p>➂ Applications include industrial automation (e.g., drone/robot localization), smart home remote controls, and anti-spoofing for keyless car entry systems, demonstrating broad scalability across embedded systems.</p>
Related Articles
- AIOT: A Convergence Of Intelligence And Connectivity3 days ago
- Construction Manuals for Affordable and AI-Capable Dronesabout 1 month ago
- Artificial Intelligence in Miniature Format for Small Devicesabout 2 months ago
- When Tiny Tech Meets Tiny Creatures In The Lab4 months ago
- IoT Platforms For On-Device Generative AI4 months ago
- Reference Design For Secure Telehealth4 months ago
- Using R To Analyse An IoT Connected Health Monitoring System4 months ago
- AI Vehicle Predictive Maintenance4 months ago
- Smallest Spy Video Streaming Camera5 months ago
- Powerful MCUs For Smart, Multi-Use AI5 months ago