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
- Overview of various stages in the TinyML workflow
- Key characteristics of edge hardware
- Strategic considerations for pipeline design
Data Acquisition and Preprocessing
- Gathering structured and sensor-based data
- Strategies for data labeling and augmentation
- Preparing datasets suitable for resource-constrained environments
Model Development for TinyML
- Selecting appropriate model architectures for microcontrollers
- Implementing training workflows using standard ML frameworks
- Evaluating key model performance indicators
Model Optimization and Compression
- Applying quantization techniques
- Utilizing pruning and weight sharing methods
- Balancing model accuracy against resource limitations
Model Conversion and Packaging
- Exporting models to TensorFlow Lite
- Integrating models into embedded toolchains
- Managing model size and memory constraints
Deployment on Microcontrollers
- Flashing models onto specific hardware targets
- Configuring run-time environments
- Conducting real-time inference tests
Monitoring, Testing, and Validation
- Implementing testing strategies for deployed TinyML systems
- Debugging model behavior directly on hardware
- Validating performance under field conditions
Integrating the Complete End-to-End Pipeline
- Building automated workflows
- Versioning data, models, and firmware
- Managing updates and iterative improvements
Summary and Next Steps
Requirements
- A solid understanding of machine learning fundamentals
- Practical experience in embedded programming
- Familiarity with Python-based data workflows
Intended Audience
- AI engineers
- Software developers
- Embedded systems experts
