Get in Touch

Course Outline

TinyML Pipeline Fundamentals

  • Insight into TinyML workflow phases
  • Attributes of edge hardware
  • Strategic considerations for pipeline architecture

Data Acquisition and Preparation

  • Gathering structured and sensor data
  • Techniques for data labelling and augmentation
  • Adapting datasets for resource-limited environments

TinyML Model Creation

  • Choosing model architectures for microcontrollers
  • Training procedures using standard ML frameworks
  • Assessing model performance metrics

Model Refinement and Compression

  • Quantisation methods
  • Pruning and weight sharing techniques
  • Striking a balance between accuracy and resource limitations

Model Translation and Packaging

  • Exporting models to TensorFlow Lite
  • Integrating models within embedded toolchains
  • Managing model footprint and memory usage

Microcontroller Deployment

  • Writing models to hardware targets
  • Setting up run-time environments
  • Testing real-time inference capabilities

Monitoring, Testing, and Verification

  • Test methodologies for deployed TinyML systems
  • Debugging model behaviour on hardware
  • Validating performance in field conditions

Assembling the Complete End-to-End Pipeline

  • Creating automated workflows
  • Version control for data, models, and firmware
  • Overseeing updates and iterations

Conclusion and Future Directions

Requirements

  • A solid grasp of core machine learning concepts
  • Proficiency in embedded programming
  • Knowledge of Python-centric data workflows

Target Audience

  • AI engineers
  • Software developers
  • Embedded systems specialists
 21 Hours

Upcoming Courses

Related Categories