Get in Touch
 Duration 21 hours

Course Outline

Introduction to Edge AI and TinyML

  • Overview of edge-based AI applications
  • Advantages and hurdles of on-device AI execution
  • Applications in robotics and automation

Core Principles of TinyML

  • Machine learning adapted for resource-constrained systems
  • Techniques for model quantization, pruning, and compression
  • Compatible frameworks and hardware ecosystems

Model Creation and Transformation

  • Developing lightweight models with TensorFlow or PyTorch
  • Migrating models to TensorFlow Lite and PyTorch Mobile
  • Verifying model precision and accuracy

Implementing On-Device Inference

  • Deploying AI models onto embedded boards (Arduino, Raspberry Pi, Jetson Nano)
  • Connecting inference processes with robotic perception and control
  • Executing real-time predictions and tracking performance

Optimizing for Edge Efficiency

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

Edge AI Ecosystems and Toolsets

  • Utilizing TensorFlow Lite and Edge Impulse
  • Reviewing PyTorch Mobile deployment strategies
  • Troubleshooting and refining embedded ML processes

Applied Integration and Real-World Examples

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

Conclusion and Future Directions

Requirements

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

Target Audience

  • Embedded developers
  • Robotics engineers
  • System integrators focused on intelligent devices

Number of participants


Price per participant

Testimonials (2)

Upcoming Courses

Related Categories