Lecture
Where Should the AI Run? Making the MCU, NPU, or Cloud Decision
- at -
- Hall C5C5.100
- Language: English
- Type: Lecture
Lecture description
Presents a practical framework for deciding whether an edge AI workload should run on a standard MCU, dedicated AI acceleration, or the cloud, based on model complexity, latency, memory, power, and connectivity/privacy requirements, illustrated with an open-source AI model on a Cortex-M-class device.
