Overview
Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Learn the fundamentals of Generative AI through this comprehensive 36-minute tutorial that covers essential concepts and includes a hands-on coding demonstration. Explore what Generative AI is and how it differs from traditional AI approaches, then dive into Large Language Models (LLMs) to understand their architecture and functionality. Discover the concept of tokens in AI processing and learn about AI inferencing - the process by which trained models generate responses. Examine the role of GPUs in AI computing, including their current limitations in handling large-scale AI workloads. Follow along with a practical demonstration building a high-speed coding assistant using Cerebras AI infrastructure, showcasing how to create an AI tool capable of generating 1,000 lines of JavaScript code in just 4 seconds. Master key terminology and concepts including model training, inference optimization, and the hardware requirements for running modern AI applications, while gaining hands-on experience with cutting-edge AI development tools and platforms.
Syllabus
00:00 Announcements
03:18 Introduction
04:45 Introduction to AI
09:53 What is GenAI?
10:39 What are LLMs?
12:42 What are tokens?
14:12 What is AI inferencing?
16:06 Introduction to GPUs
17:35 GPU limitations
19:30 Demo
33:45 Closing remarks
Taught by
Kunal Kushwaha