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.
Course Outline
Foundations of TinyML Pipelines
- Overview of the TinyML workflow stages
- Key characteristics of edge hardware
- Essential considerations in pipeline design <\/ul>
- Gathering structured and sensor data
- Strategies for data labeling and augmentation
- Preparing datasets suitable for constrained environments <\/ul>
- Choosing model architectures appropriate for microcontrollers
- Training workflows using standard ML frameworks
- Evaluating key model performance metrics <\/ul>
- Quantization techniques
- Pruning and weight sharing methods
- Balancing accuracy against resource limitations <\/ul>
- Exporting models to TensorFlow Lite
- Integrating models into embedded toolchains
- Managing model size and memory constraints <\/ul>
- Flashing models onto hardware targets
- Configuring run-time environments
- Conducting real-time inference testing <\/ul>
- Testing strategies for deployed TinyML systems
- Debugging model behavior on hardware
- Validating performance in field conditions <\/ul>
- Building automated workflows
- Versioning data, models, and firmware
- Managing updates and iterations <\/ul>
Data Collection and Preprocessing
Model Development for TinyML
Model Optimization and Compression
Model Conversion and Packaging
Deployment on Microcontrollers
Monitoring, Testing, and Validation
Integrating the Full End-to-End Pipeline
Summary and Next Steps
Requirements
- A solid understanding of machine learning fundamentals
- Prior experience with embedded programming
- Familiarity with Python-based data processing workflows <\/ul>
- AI engineers
- Software developers
- Embedded systems specialists <\/ul>
Target Audience
21 Hours
