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
- Exploring the stages of the TinyML workflow
- Understanding the unique traits of edge hardware
- Key factors in pipeline architecture
Data Acquisition and Refinement
- Acquiring structured and sensor-based data
- Strategies for labeling and data augmentation
- Optimizing datasets for resource-limited environments
Developing Models for TinyML
- Choosing appropriate model architectures for microcontrollers
- Training processes leveraging standard ML frameworks
- Assessing key model performance metrics
Optimizing and Compressing Models
- Applying quantization methods
- Implementing pruning and weight sharing
- Striking a balance between accuracy and resource limitations
Model Transformation and Packaging
- Converting models to TensorFlow Lite
- Incorporating models into embedded development toolchains
- Navigating model size and memory restrictions
Implementing on Microcontrollers
- Writing models to hardware targets
- Setting up runtime environments
- Conducting real-time inference tests
Oversight, Verification, and Validation
- Approaches to testing deployed TinyML systems
- Diagnosing model performance on physical hardware
- Validating performance under field conditions
Assembling the Complete End-to-End Workflow
- Establishing automated processing workflows
- Managing versions of data, models, and firmware
- Handling updates and continuous iteration
Wrap-Up and Future Directions
Requirements
- A solid grasp of core machine learning principles
- Practical experience in embedded programming
- Proficiency in Python-based data processing workflows
Target Audience
- AI Engineers
- Software Developers
- Embedded Systems Specialists
