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
Basics of TinyML Workflows
- Review of TinyML process stages
- Attributes of edge hardware
- Key considerations in pipeline architecture
Data Acquisition and Preprocessing
- Acquiring structured and sensor-based data
- Methods for data labeling and augmentation
- Dataset preparation for resource-limited settings
Model Creation for TinyML
- Choosing suitable architectures for microcontrollers
- Training processes utilizing common ML frameworks
- Assessing model performance metrics
Model Refinement and Reduction
- Application of quantization methods
- Pruning and weight sharing techniques
- Optimizing the trade-off between accuracy and resource usage
Model Transformation and Bundling
- Exporting models to TensorFlow Lite
- Embedding models within embedded development toolchains
- Managing model dimensions and memory limitations
Implementation on Microcontrollers
- Loading models onto hardware targets
- Setting up runtime environments
- Testing real-time inference capabilities
Oversight, Testing, and Verification
- Testing approaches for deployed TinyML systems
- Troubleshooting model behavior on hardware
- Validating performance in field conditions
Assembling the Complete End-to-End Pipeline
- Creating automated workflows
- Version control for data, models, and firmware
- Managing updates and iterative improvements
Conclusion and Future Directions
Requirements
- A solid grasp of machine learning core concepts
- Practical experience in embedded development
- Proficiency with Python-based data pipelines
Target Audience
- AI Specialists
- Software Engineers
- Embedded Systems Professionals
