Course Outline

Introduction to Edge AI and NVIDIA Jetson

  • Overview of edge AI applications
  • Introduction to NVIDIA Jetson hardware
  • JetPack SDK components and development environment

Setting Up the Development Environment

  • Installing JetPack SDK and setting up the Jetson board
  • Understanding TensorRT and model optimization
  • Configuring the runtime environment

Optimizing AI Models for Edge Deployment

  • Model quantization and pruning techniques
  • Using TensorRT for model acceleration
  • Converting models to ONNX format

Deploying AI Models on Jetson Devices

  • Running inference with TensorRT
  • Integrating AI models with real-time applications
  • Optimizing performance and reducing latency

Computer Vision and Deep Learning on Jetson

  • Deploying image classification and object detection models
  • Using AI for real-time video analytics
  • Implementing AI-powered robotics applications

Edge AI Security and Performance Optimization

  • Securing AI models on edge devices
  • Power efficiency and thermal management
  • Scaling AI applications on Jetson platforms

Project Implementation and Real-World Use Cases

  • Building an AI-powered IoT solution
  • Deploying AI in autonomous systems
  • Case studies of AI on edge devices

Summary and Next Steps

Requirements

  • Experience with AI model training and inference
  • Basic knowledge of embedded systems
  • Familiarity with Python programming

Audience

  • AI developers
  • Embedded engineers
  • Robotics engineers
 21 Hours

Related Categories