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
- Exploring the limitations and potential of TinyML
- Surveying prevalent microcontroller platforms
- Contrasting Raspberry Pi with Arduino and alternative boards
Hardware Preparation and Setup
- Setting up Raspberry Pi OS
- Setting up Arduino boards
- Linking sensors and auxiliary devices
Data Acquisition Methods
- Recording sensor information
- Processing audio, motion, and environmental data
- Assembling annotated datasets
Model Design for Edge Hardware
- Choosing appropriate model architectures
- Training TinyML models using TensorFlow Lite
- Assessing performance metrics for embedded contexts
Model Refinement and Conversion
- Applying quantization techniques
- Adapting models for microcontroller deployment
- Optimising memory usage and computational load
Deployment on Raspberry Pi
- Executing TensorFlow Lite inference
- Incorporating model outputs into broader applications
- Resolving performance-related challenges
Deployment on Arduino
- Leveraging the Arduino TensorFlow Lite Micro library
- Writing models to microcontrollers
- Validating accuracy and runtime behaviour
Constructing Comprehensive TinyML Applications
- Designing integrated embedded AI workflows
- Building interactive, real-world prototypes
- Validating and improving project functionality
Conclusion and Future Directions
Requirements
- A foundational grasp of basic programming principles
- Prior experience in operating microcontrollers
- Knowledge of Python or C/C++ programming languages
Target Audience
- Makers
- Enthusiasts and hobbyists
- Developers specialising in embedded AI
