Applied Edge AI

• Familiarity with cloud computing and artifical intelligence

Audience

• Business Analysts
• Product managers
• Developers

Applied Edge AI is the power of artificial intelligence with edge computing, offering a comprehensive exploration of deploying AI models on edge devices. This instructor-led, live training covers CNN Architectures, knowledge distillation, and federated learning techniques. Participants will engage in practical sessions, applying AI to real-world scenarios, optimizing model performance, and ensuring efficient data processing at the edge.

By the end of this training, participants will be able to:

• Implement compact network designs and deep compression methods for edge devices.
• Utilize federated learning for decentralized AI model training.
• Deploy and manage AI-driven applications efficiently on edge devices.

Format of the Course

• Interactive lecture and discussion.
• Lots of exercises and practice.
• Hands-on implementation in a live-lab environment.

Course Customization Options

• To request a customized training for this course, please contact us to arrange.

• Introduction to Edge AI
  • Defining Edge AI and its significance
  • Benefits of deploying AI models at the edge
  • Overview of the AI landscape for edge computing
• Convolutional Neural Networks (CNN) Architectures for Edge AI
  • Understanding CNN basics and their applicability to Edge AI
  • Design considerations for CNNs on edge devices
  • Case studies: Efficient CNN models in action
• Designing Compact Networks for Edge Deployment
  • Techniques for reducing model size without sacrificing accuracy
  • Tools and frameworks for model optimization
  • Evaluating trade-offs between performance and complexity
• Techniques in Knowledge Distillation for Edge AI
  • Principles of knowledge distillation and its benefits
  • Implementing knowledge distillation for edge models
  • Practical examples and success stories
• Deep Compression Methods for Edge AI Models
  • Overview of model compression techniques (pruning, quantization)
  • Application of compression methods to edge AI scenarios
  • Impact on performance, accuracy, and model deployment
• Federated Learning Concepts and Applications
  • Introduction to federated learning and its importance for privacy and efficiency
  • Architectural and operational aspects of federated learning systems
  • Challenges and solutions in implementing federated learning at the edge
• Implementing Edge AI Solutions
  • End-to-end workflow for deploying AI models on edge devices
  • Tools and platforms supporting Edge AI development
  • Monitoring and managing Edge AI applications in production
• Case Studies and Project Work
  • Analyzing real-world Edge AI deployments across various sectors
  • Group project: Design and implement an Edge AI solution
  • Presentation and critique of project outcomes