Build Your Intelligent Edge

Overview

Explore IoT solutions that bring cloud-trained AI and ML closer to devices, enabling offline scenarios and improved product performance near customers.

Syllabus

• Introduction to Edge Computing
Overview of IoT and Edge Computing
Key advantages of running AI/ML at the edge
• Cloud vs. Edge: A Comparative Analysis
Differences in architecture and data processing
Use cases for cloud-trained models on edge devices
• Building AI Models for Edge Deployment
Designing lightweight and efficient models
Training AI models in the cloud for edge use
• Optimizing AI Performance on Edge Devices
Techniques for reducing latency and improving efficiency
Tools and frameworks for edge AI optimization
• Implementing Machine Learning (ML) on Edge Devices
Overview of common ML algorithms for edge
Case studies: successful ML edge deployments
• Edge AI Hardware and Software Platforms
Popular hardware for edge computing (e.g., GPUs, TPUs)
Software platforms and tools (e.g., TensorFlow Lite, ONNX)
• IoT Infrastructure and Connectivity for Edge AI
Network architectures supporting edge deployments
Managing data flow between edge devices and the cloud
• Security and Privacy in Edge Computing
Protecting data integrity and privacy at the edge
Implementing secure edge AI systems
• Developing Offline Capabilities in Edge AI
Designing for connectivity interruptions
Case examples of offline-ready edge applications
• Real-world Applications and Case Studies
Industry-specific uses of edge AI (e.g., retail, healthcare)
Lessons learned from real deployments
• Building and Deploying Edge AI Solutions
Steps for deploying a project from conception to execution
Best practices and tips for successful implementation
• Future Trends in Edge Computing
Innovations and emerging technologies in edge AI
Predictions for the evolution of intelligent edge solutions
• Conclusion and Course Review
Summary of key learnings
Next steps and further learning resources

---

Subjects

Conference Talks