Learn Edge AI / TinyML
Deploy machine learning models to edge devices, microcontrollers, and mobile phones. Master TensorFlow Lite, ONNX Runtime, quantization, pruning, and on-device inference — all for free.
Your Learning Path
Follow these lessons in order, or jump to any topic that interests you.
1. Introduction
What is Edge AI? On-device inference, TinyML, and why moving AI to the edge matters.
2. Hardware
Microcontrollers, Raspberry Pi, NVIDIA Jetson, Google Coral, and AI accelerators.
3. TensorFlow Lite
Convert, optimize, and run TensorFlow models on mobile and microcontroller devices.
4. ONNX Runtime
ONNX format, ONNX Runtime, CoreML, and cross-platform model deployment.
5. Deployment
Quantization, pruning, knowledge distillation, and deploying to Raspberry Pi and mobile.
6. Best Practices
Model selection, profiling, power management, OTA updates, and production edge AI.
What You'll Learn
By the end of this course, you will be able to:
Understand Edge AI
Know when and why to run ML on edge devices instead of the cloud.
Optimize Models
Apply quantization, pruning, and distillation to shrink models for constrained devices.
Deploy Everywhere
Use TFLite, ONNX, and CoreML to deploy models to phones, Raspberry Pi, and microcontrollers.
Build IoT AI
Create real-time inference applications for IoT, wearables, and embedded systems.