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 constraints and potential of TinyML
- Overview of prevalent microcontroller platforms
- Comparative analysis of Raspberry Pi, Arduino, and other boards
Hardware Preparation and Configuration
- Setting up the Raspberry Pi OS
- Configuring Arduino boards
- Linking sensors and peripheral devices
Data Acquisition Techniques
- Capturing sensor inputs
- Managing audio, motion, and environmental data streams
- Generating labeled datasets
Model Development for Edge Devices
- Choosing appropriate model architectures
- Training TinyML models utilizing TensorFlow Lite
- Assessing performance for embedded applications
Model Refinement and Conversion
- Applying quantization strategies
- Translating models for microcontroller deployment
- Optimizing memory usage and computational efficiency
Deployment on Raspberry Pi
- Executing TensorFlow Lite inference
- Integrating model outputs into applications
- Diagnosing and resolving performance issues
Deployment on Arduino
- Leveraging the Arduino TensorFlow Lite Micro library
- Flashing models onto microcontrollers
- Validating accuracy and execution behavior
Assembling Complete TinyML Applications
- Designing comprehensive embedded AI workflows
- Implementing interactive, real-world prototypes
- Testing and refining project functionality
Summary and Next Steps
Requirements
- A solid grasp of fundamental programming concepts
- Practical experience in operating microcontrollers
- Proficiency in Python or C/C++
Target Audience
- Makers
- Hobbyists
- Embedded AI developers
