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
TinyML Pipeline Fundamentals
- Introduction to the stages of the TinyML workflow
- Key characteristics of edge hardware
- Considerations for effective pipeline design
Data Acquisition and Preprocessing
- Gathering structured and sensor-based data
- Strategies for data labeling and augmentation
- Adapting datasets for resource-constrained environments
Developing Models for TinyML
- Choosing appropriate model architectures for microcontrollers
- Implementing training workflows with standard ML frameworks
- Assessing model performance metrics
Optimizing and Compressing Models
- Applying quantization techniques
- Utilizing pruning and weight sharing
- Striking a balance between accuracy and resource limitations
Converting and Packaging Models
- Exporting models to TensorFlow Lite
- Integrating models within embedded toolchains
- Navigating model size and memory constraints
Deployment to Microcontrollers
- Flashiing models to hardware targets
- Setting up run-time environments
- Conducting real-time inference tests
Monitoring, Testing, and Validation
- Employing testing strategies for live TinyML systems
- Troubleshooting model behavior on hardware
- Validating performance under field conditions
Assembling the Complete End-to-End Pipeline
- Constructing automated workflows
- Managing versions of data, models, and firmware
- Overseeing updates and iterative improvements
Conclusion and Future Directions
Requirements
- A solid grasp of machine learning fundamentals
- Practical experience in embedded programming
- Proficiency with Python-based data workflows
Intended Audience
- AI Engineers
- Software Developers
- Embedded Systems Specialists
