all
Tutorial Track

TinyML

Deploy machine learning on microcontrollers — TensorFlow Lite Micro, Edge Impulse, model quantization, and on-device inference for keyword spotting, gesture recognition, and image classification.

16 Chapters
16 Published
Free Access
CCS IDE
100% complete
Start Learning
TinyML board
1
Introduction to TinyML Published

What is TinyML, the ML-on-MCU ecosystem, hardware constraints, and real-world use cases.

2
TinyML Workflow Overview Published

End-to-end pipeline: data collection → training → conversion → deployment → inference.

3
Setting Up TFLite Micro Published

Add TensorFlow Lite for Microcontrollers to an Arduino, STM32, or ESP32 project.

4
Setting Up Edge Impulse Published

Create a project, connect a device, and use the Edge Impulse Studio for end-to-end ML.

5
Data Collection & Preprocessing Published

Capture sensor data from IMU, microphone, and camera; label datasets; handle class imbalance.

6
Training a Model in Google Colab Published

Build and train a small neural network with Keras, evaluate accuracy, and export to TFLite.

7
Model Quantization & Pruning Published

Post-training int8 quantization, quantization-aware training, and weight pruning techniques.

8
Converting to TFLite & TFLite Micro Published

Use TFLiteConverter, generate a C byte array, and link it into your firmware build system.

9
Keyword Spotting (Wake Word) Published

Train a yes/no or custom wake-word model, deploy on a Cortex-M board with a PDM microphone.

10
Gesture Recognition with IMU Published

Classify hand gestures from accelerometer/gyroscope data in real time on-device.

11
Anomaly Detection Published

Use autoencoders and K-means for predictive maintenance on vibration and temperature sensors.

12
Person Detection with Camera Published

Run MobileNet V1 person detection on ESP32-CAM or Arducam using TFLite Micro.

13
TinyML on ESP32 with Edge Impulse Published

Deploy an Edge Impulse model on ESP32, integrate with FreeRTOS tasks, and stream results via MQTT.

14
TinyML on STM32 with X-CUBE-AI Published

Use STM32Cube.AI to convert Keras models, generate optimized C code, and run inference on Cortex-M4.

15
Optimizing Models for Cortex-M Published

Reduce latency and RAM usage: operator fusion, CMSIS-NN kernels, and flash-friendly model layout.

16
TinyML with Zephyr RTOS Published

Integrate TFLite Micro into a Zephyr application, use Zephyr sensor drivers, and manage inference threads.