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
- An overview of the various stages in the TinyML workflow
- Key attributes of edge hardware
- Critical factors in pipeline architecture
Data Acquisition and Preparation
- Gathering structured and sensor-derived data
- Strategies for data labeling and augmentation
- Preparing datasets for resource-constrained environments
Model Creation for TinyML
- Choosing appropriate model architectures for microcontrollers
- Training processes utilizing standard ML frameworks
- Assessing key model performance metrics
Model Refinement and Reduction
- Application of quantization methods
- Techniques for pruning and weight sharing
- Striking a balance between accuracy and resource limitations
Model Transformation and Bundling
- Exporting models for TensorFlow Lite
- Incorporating models into embedded toolchains
- Addressing model size and memory restrictions
Implementation on Microcontrollers
- Transferring models to specific hardware targets
- Setting up runtime environments
- Conducting real-time inference tests
Monitoring, Validation, and Testing
- Testing methodologies for live TinyML systems
- Troubleshooting model behavior on physical hardware
- Verifying performance under field conditions
Assembling the Complete End-to-End Pipeline
- Creating automated workflows
- Implementing version control for data, models, and firmware
- Overseeing updates and iterative improvements
Recap and Future Directions
Requirements
- A solid grasp of core machine learning principles
- Practical experience in embedded systems programming
- Knowledge of Python-driven data processing pipelines
Intended Participants
- Artificial Intelligence engineers
- Software engineers
- Specialists in embedded systems
