Get in Touch

Course Outline

Introduction to Edge AI and TinyML

  • An overview of edge-based AI
  • The advantages and challenges of executing AI on local devices
  • Application scenarios in robotics and automation

TinyML Fundamentals

  • Machine learning techniques for resource-constrained systems
  • Methods for model quantization, pruning, and compression
  • Review of supported frameworks and hardware platforms

Model Development and Conversion

  • Training lightweight models with TensorFlow or PyTorch
  • Converting models to formats compatible with TensorFlow Lite and PyTorch Mobile
  • Testing and validating model precision

Implementing On-Device Inference

  • Deploying AI models on embedded boards such as Arduino, Raspberry Pi, and Jetson Nano
  • Integrating inference processes with robotic perception and control loops
  • Executing real-time predictions and monitoring system performance

Optimizing for Edge Performance

  • Minimizing latency and energy expenditure
  • Leveraging hardware acceleration via NPUs and GPUs
  • Benchmarking and profiling embedded inference workflows

Edge AI Frameworks and Tools

  • Utilizing TensorFlow Lite and Edge Impulse
  • Examining deployment options with PyTorch Mobile
  • Debugging and refining embedded ML processes

Practical Integration and Case Studies

  • Architecting edge AI perception systems for robotic applications
  • Combining TinyML with ROS-based robotics architectures
  • Case study analyses: autonomous navigation, object detection, and predictive maintenance

Conclusion and Future Directions

Requirements

  • A solid understanding of embedded systems
  • Proficiency in Python or C++ programming
  • Knowledge of fundamental machine learning concepts

Target Audience

  • Embedded developers
  • Robotics engineers
  • System integrators specializing in intelligent devices
 21 Hours

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories