Get in Touch
 Duration 21 hours

Course Outline

Introduction to Edge AI and TinyML

  • Overview of AI operations at the edge
  • Advantages and challenges of on-device AI execution
  • Applications in robotics and automation

Foundations of TinyML

  • Applying machine learning to resource-constrained systems
  • Techniques for model quantization, pruning, and compression
  • Supported frameworks and compatible hardware platforms

Model Development and Transformation

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

Implementing On-Device Inference

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

Optimizing for Edge Performance

  • Minimizing latency and energy consumption
  • Leveraging hardware acceleration via NPUs and GPUs
  • Benchmarking and profiling embedded inference workloads

Edge AI Frameworks and Tooling

  • Utilizing TensorFlow Lite and Edge Impulse
  • Investigating PyTorch Mobile deployment strategies
  • Debugging and optimizing embedded ML workflows

Practical Integration and Case Analyses

  • Designing edge AI perception systems for robots
  • Integrating TinyML with ROS-based robotics architectures
  • Case studies: autonomous navigation, object detection, and predictive maintenance

Conclusion and Future Directions

Requirements

  • Solid knowledge of embedded systems
  • Proficiency in Python or C++ programming
  • Basic familiarity with machine learning concepts

Intended Audience

  • Embedded developers
  • Robotics engineers
  • System integrators focused on intelligent device development

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories