Edge AI
The deployment of AI algorithms on edge devices, enabling data processing and decision-making at the source of data generation.
Definition
Moves computation from centralized clouds to local devices (smart cameras, IoT sensors), reducing latency, preserving bandwidth, and enhancing privacy by keeping raw data on-device. Edge AI requires model compression (quantization, pruning), hardware-aware optimization, and robust update mechanisms. Governance covers version control, security patches, and performance monitoring at the edge.
Real-World Example
A factory installs edge AI on its assembly-line cameras to detect product defects in real time. The compressed model runs on on-site GPU servers, sending only defect alerts to the cloud—minimizing network use and ensuring immediate response without uploading sensitive IP images externally.
.svg)
