Generative AI at the Edge: Design, Deploy, and Optimize Generative AI Models
Generative AI at the Edge: Design, Deploy, and Optimize Generative AI Models
.MP4, AVC, 1280x720, 30 fps | English, AAC, 2 Ch | 1h 4m | 176 MB
Instructors: Karl Obinna Amalu, Kesha Williams
.MP4, AVC, 1280x720, 30 fps | English, AAC, 2 Ch | 1h 4m | 176 MB
Instructors: Karl Obinna Amalu, Kesha Williams
In this course, tech leaders Karl Obinna Amalu and Kesha Williams present a hands-on learning experience, exploring the integration of Generative AI (GenAI) with edge computing using the Google Distributed Edge platform. Learn how to design, develop, deploy, and optimize AI models on edge devices, ensuring low latency and efficient performance, and discover opportunities to practice what you learn. Dive into model compatibility, deployment strategies, performance optimization, and ongoing management of edge AI deployments. Plus, gain insights into the broader landscape of edge computing and its applications. By the end of the course, you will have the skills to implement effective edge AI solutions in real-world scenarios.
Learning objectives
- Design and develop Generative AI models optimized for edge deployment, ensuring compatibility with edge devices.
- Deploy and manage GenAI models on the Google Distributed Edge platform, using effective deployment strategies and techniques.
- Apply performance optimization techniques to improve the efficiency and responsiveness of edge-deployed AI models.
- Monitor and maintain edge AI deployments, utilizing tools and methods to ensure ongoing performance and reliability.
- Understand the broader scope of edge computing, including its evolution and potential applications across various domains.
Generative AI at the Edge: Design, Deploy, and Optimize Generative AI Models
