Edge AI: Tools and Best Practices for Building AI Applications at the Edge

Edge AI: Tools and Best Practices for Building AI Applications at the Edge

1h 19mIntermediate2024-01-09

Authors

Kumaran Ponnambalam

Kumaran Ponnambalam

Working with data for 20+ years

Course details

As edge devices like smartphones, cameras, and sensors become more powerful, the applications that manage them are moving from the cloud to edge. More and more AI models are now deployed on these devices in an attempt to reduce latency and secure greater levels of privacy. As a result, the AI community needs to familiarize itself with how to successfully build edge AI applications.

If you’re currently working on building AI applications in the enterprise or the cloud, or just looking to expand your existing skill set, this course is designed to help you get up to speed with exciting new developments in machine learning applications. Along the way, instructor Kumaran Ponnambalam covers a handful of real-world edge AI use cases drawn from industries such as retail, healthcare, transportation, manufacturing, and more.

Note: This course requires a basic working knowledge of machine learning processes, practices, and applications.

Skills covered

Programming FoundationsCloud AdministrationArtificial Intelligence FoundationsArtificial Intelligence (AI)Cloud ComputingSoftware DevelopmentOne-Off

Concepts

Introduction

  • Why AI at the edge

Edge Computing and Artificial Intelligence

  • Internet of Things
  • What is edge computing
  • Benefits of edge computing
  • Challenges of edge computing
  • AI at the edge
  • Benefits and challenges of edge AI

Edge AI Use Cases

  • Personal edge AI
  • Retail edge AI
  • Healthcare edge AI
  • Transport edge AI
  • Manufacturing edge AI

Infrastructure for Edge AI

  • Data for edge AI
  • Processors for edge AI
  • Devices and servers for edge AI
  • Software infrastructure for edge AI
  • Edge AI-specialized software

Training Models for Edge Deployments

  • Building a model baseline
  • Model compression
  • Model optimization for the edge
  • Testing models before deployments
  • Federated learning

Edge AI Deployment and Operations

  • Edge AI deployment architectures
  • Deploying AI at the edge
  • Model inference at the edge
  • Edge AI data collection
  • Publishing data from the edge
  • Edge AI performance analysis

Best Practices for Building Edge AI Applications

  • Infrastructure selection best practices
  • Model selection and training best practices
  • Model optimization best practices
  • Model deployment best practices
  • Data collection and analytics best practices

Conclusion

  • Building more with edge AI
40,000 Toman