Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Duration 21 hours
Course Outline
Introduction to TinyML
- Examining TinyML constraints and capabilities
- Overview of prevalent microcontroller platforms
- Comparison of Raspberry Pi, Arduino, and other boards
Hardware Setup and Configuration
- Configuring the Raspberry Pi OS
- Setting up Arduino boards
- Integration of sensors and peripherals
Data Collection Techniques
- Acquiring sensor data
- Processing audio, motion, and environmental inputs
- Generating labeled datasets
Model Development for Edge Devices
- Choosing appropriate model architectures
- Training TinyML models using TensorFlow Lite
- Assessing performance for embedded applications
Model Optimization and Conversion
- Quantization methodologies
- Adapting models for microcontroller implementation
- Optimizing memory and computational efficiency
Deployment on Raspberry Pi
- Executing TensorFlow Lite inference
- Incorporating model outputs into applications
- Resolving performance-related issues
Deployment on Arduino
- Utilizing the Arduino TensorFlow Lite Micro library
- Flashing models to microcontrollers
- Validating accuracy and execution behavior
Building Complete TinyML Applications
- Architecting comprehensive embedded AI workflows
- Developing interactive, real-world prototypes
- Testing and refining project functionality
Summary and Future Directions
Requirements
- Grasping of fundamental programming concepts
- Practical experience with microcontroller operation
- Knowledge of Python or C/C++
Target Audience
- Makers
- Hobbyists
- Embedded AI developers
