AI Ecosystem CourseBy Queensly Austin
Module 21

Edge And On-Device AI

Introduction Available · Lessons In Development

Introduction

Should a task run in a distant data center, on a nearby gateway, or on the user's device? The answer affects delay, connectivity, privacy, hardware limits, updates, and costs. Edge AI is a choice about where the work happens, with consequences for the whole product.

We will connect compute in Module 2, inference memory in Module 14, optimization in Module 16, and application architecture in Module 20. You will decide what can run locally, what needs the cloud, and how to test a combination of both. The project is an offline study assistant that explains selected course material and preserves progress.

Start with placement and hardware, then optimization and operations, and finish with the local-versus-cloud comparison. Keep returning to the task: will the proposed setup work on the actual device, network, and user conditions?

Planned lessons

  1. What Counts As The Edge?
  2. Why Place Computation Locally?
  3. CPUs, GPUs, And NPUs
  4. Memory Is More Than The Model File
  5. Battery, Power, Energy, And Heat
  6. Compression And Smaller Models
  7. Conversion, Runtime Compatibility, And Packaging
  8. Hybrid Local-Cloud Architecture
  9. Local Retrieval And Personalization
  10. Privacy And Security Across Device Boundaries
  11. Deployment To A Fragmented Device Fleet
  12. Measuring The Whole Local Experience
  13. Hardware-Feature Economics And Cloud-Service Economics
  14. Streaming Tasks And Deadline Budgets
  15. Federated Learning And Local Adaptation Boundaries