Get in Touch

Course Outline

Foundations of TinyML

  • Exploring the limitations and potential of TinyML
  • Overview of prevalent microcontroller architectures
  • Comparative analysis of Raspberry Pi, Arduino, and alternative boards

Hardware Preparation and Setup

  • Setting up the Raspberry Pi operating system
  • Configuring Arduino environments
  • Interfacing sensors and peripheral devices

Data Acquisition Methods

  • Recording sensor inputs
  • Processing audio, motion, and environmental metrics
  • Constructing annotated datasets

Model Creation for Edge Computing

  • Choosing appropriate model architectures
  • Training TinyML models utilizing TensorFlow Lite
  • Assessing performance for embedded scenarios

Model Refinement and Conversion

  • Applying quantization techniques
  • Adapting models for microcontroller execution
  • Optimizing memory usage and computational efficiency

Implementation on Raspberry Pi

  • Executing TensorFlow Lite inference
  • Incorporating model outputs into broader applications
  • Diagnosing and resolving performance bottlenecks

Implementation on Arduino

  • Leveraging the Arduino TensorFlow Lite Micro library
  • Writing models to microcontroller storage
  • Validating accuracy and runtime behavior

Assembling Complete TinyML Systems

  • Architecting comprehensive embedded AI workflows
  • Building interactive, real-world prototypes
  • Conducting testing and iterative refinement of project features

Conclusion and Future Directions

Requirements

  • A solid grasp of fundamental programming principles
  • Practical experience in utilizing microcontrollers
  • Proficiency in Python or C/C++

Target Audience

  • Maker community members
  • Technology hobbyists
  • Developers specializing in embedded AI
 21 Hours

Upcoming Courses

Related Categories