TinyML brings machine learning to microcontrollers with severe memory (<256KB RAM) and compute constraints. Post-training quantization converts FP32 weights to INT8.
Key Uses:
Wake-word detection, predictive maintenance sensors, and always-on vision on embedded devices.
Hacks:
Dynamic range quantization and float16/INT8 mixed precision. Pruning (magnitude-based weight removal) followed by fine-tuning. Knowledge distillation from large teacher to tiny student model. Use TensorFlow Lite Micro or Edge Impulse for optimized deployment.