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
Core Principles of TinyML Pipelines
- Overview of TinyML workflow phases
- Attributes of edge hardware
- Factors in pipeline architecture
Data Gathering and Preprocessing
- Acquiring structured and sensor data
- Techniques for data labeling and augmentation
- Structuring datasets for resource-limited environments
Model Development for TinyML
- Choosing model architectures for microcontrollers
- Training processes using standard ML frameworks
- Assessing model performance metrics
Model Optimization and Reduction
- Quantization methods
- Pruning and weight sharing techniques
- Optimizing the balance between accuracy and resource usage
Model Conversion and Packaging
- Exporting models to TensorFlow Lite
- Integrating models into embedded toolchains
- Managing model size and memory limitations
Deployment on Microcontrollers
- Flashing models to hardware targets
- Setting up run-time environments
- Testing real-time inference
Monitoring, Testing, and Verification
- Testing methods for deployed TinyML systems
- Diagnosing model behavior on hardware
- Validating performance in field conditions
Integrating the Full End-to-End Pipeline
- Creating automated workflows
- Version control for data, models, and firmware
- Overseeing updates and iterations
Wrap-Up and Future Steps
Requirements
- Knowledge of fundamental machine learning concepts
- Background in embedded programming
- Experience with Python-based data processing workflows
Target Audience
- AI engineers
- Software developers
- Embedded systems specialists
