Edge AI Model Compression and AutoML for Tiny Edge Devices

Practical pathway covering compression, quantization, pruning, distillation, and hardware‑aware AutoML to deploy efficient AI on tiny edge devices under strict latency, memory, and energy limits.

After completing this Pathway, you will be able to:

• Apply quantization and pruning on microcontroller models
• Evaluate trade‑offs using AutoML to optimise latency and accuracy