18
Edge AI & TinyML
Model optimization, quantization, and deployment to mobile and IoT
3 lessons130 min totaladvanced
1
Model Optimization
Quantization (INT8, INT4, dynamic vs static), pruning, knowledge distillation, and neural architecture search for efficiency
2 exercisesQuiz45m
2
TF Lite, Core ML & Inference Runtimes
TF Lite conversion and inference, Core ML with coremltools, ONNX Runtime, TensorRT, and model benchmarking
2 exercisesQuiz45m
3
IoT & Microcontroller Deployment
TF Lite Micro, edge TPUs, Jetson deployment, real-world constraints, and OTA model updates
2 exercisesQuiz40m