What the course covers.
- Module 1
Edge AI Fundamentals & Hardware Constraints
Learners begin by understanding the challenges and opportunities of running AI on edge devices. This module covers low-power computing, embedded system architectures, memory and processing limitations, and performance trade-offs. Participants learn how to design AI pipelines suited for real-world edge applications.
- Module 2
Model optimisation & Quantisation
This module focuses on adapting AI models for edge deployment. Topics include pruning, quantisation, knowledge distillation, and lightweight model design. Learners implement practical techniques to reduce model size and computational load while maintaining accuracy, ensuring AI models run efficiently on constrained hardware.
- Module 3
Deployment & Real-Time Edge Applications
Learners gain hands-on experience deploying AI models to edge devices and embedded systems. The module covers microcontrollers, embedded GPUs, IoT devices, and real-time inference. Participants also learn best practices for monitoring, updating, and maintaining AI applications in production environments.
