Modern Generative AI is capable of generating entire stories and photorealistic images, but how do these models actually work? As it turns out, the field of physics is actually the inspiration for many of these state-of-the-art Generative AI models. In this video, we'll take a high-level look at how methods from physics are inspiring modern Generative AI. We will focus on intuition, first taking a look at how these methods work in general, and then taking a look at two examples in particular. The first uses the subfield of electrostatics, and the second uses the field of thermodynamics. [1] Solving the heat equation - https://www.youtube.com/watch?v=ToIXSwZ1pJU ▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬▬ 🖥️ Website: https://www.assemblyai.com/discover/?utm_source=youtube&utm_medium=referral&utm_campaign=yt_ry_4 🐦 Twitter: https://twitter.com/AssemblyAI 🦾 Discord: https://discord.gg/Cd8MyVJAXd ▶️ Subscribe: null 🔥 We're hiring! Check our open roles: https://www.assemblyai.com/careers ▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬ 0:00 Intro 0:32 Sampling from data distributions 1:24 How Generative AI works 1:42 How Physics comes into play 2:36 Poisson Flow Generative Models (PFGMs) 3:59 How PFGMs work in practice 4:38 Diffusion Models 5:10 What is Thermodynamics? 6:27 Random walks 7:20 Random walks and Diffusion Models 8:26 2024's AI Essentials: 10 Must-Know AI terms #MachineLearning #DeepLearning