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 TinyML limitations and potential
- Overview of prevalent microcontroller platforms
- Comparative analysis of Raspberry Pi, Arduino, and other boards
Hardware Preparation and Setup
- Configuring Raspberry Pi OS
- Setting up Arduino boards
- Linking sensors and peripherals
Data Acquisition Methods
- Recording sensor data
- Managing audio, motion, and environmental inputs
- Generating labeled datasets
Model Design for Edge Devices
- Choosing appropriate model architectures
- Training TinyML models using TensorFlow Lite
- Assessing performance for embedded applications
Model Refinement and Conversion
- Quantization techniques
- Translating models for microcontroller deployment
- Optimizing memory and computational efficiency
Deployment on Raspberry Pi
- Executing TensorFlow Lite inference
- Integrating model outputs into applications
- Resolving performance bottlenecks
Deployment on Arduino
- Leveraging the Arduino TensorFlow Lite Micro library
- Writing models to microcontrollers
- Validating accuracy and runtime behavior
Creating Complete TinyML Solutions
- Architecting end-to-end embedded AI workflows
- Building interactive, real-world prototypes
- Testing and polishing project features
Conclusion and Future Directions
Requirements
- A grasp of fundamental programming concepts
- Practical experience with microcontroller usage
- Knowledge of Python or C/C++
Target Audience
- Makers
- Hobbyists
- Embedded AI developers
