Mathematics for AI and Machine Learning

Foundations for modern AI and machine learning

Ornstein-Uhlenbeck (OU) Heat Flow

Chapter 21 Dynamics & diffusion

Chapter 21: Fokker-Planck and Distribution Dynamics — Ornstein-Uhlenbeck & Heat Equation Solutions

Animated preview (GIF)
Ornstein-Uhlenbeck (OU) Heat Flow — animated GIF preview
High-resolution PNG
Ornstein-Uhlenbeck (OU) Heat Flow — high-resolution mind-map icon

From the book

Chapter 21: Fokker-Planck and Distribution Dynamics. In the chapter mind map this icon labels **Ornstein-Uhlenbeck & Heat Equation Solutions. The discussion below is excerpted and lightly edited from § Ornstein-Uhlenbeck & Heat Equation Solutions** in Mathematics for AI and Machine Learning.

For pure diffusion (no drift, $\mathbf{f} = \mathbf{0}$), the Fokker-Planck equation becomes the heat equation:

This is exactly what happens in the forward diffusion process of diffusion models.

What this drawing shows

What you see. Red initial peak fixed; blue density relaxes toward the mean and widens under OU / heat diffusion.

In the mind map. Chapter 21 — Ornstein-Uhlenbeck & Heat Equation Solutions. See From the book above for definitions, figures, and worked examples.

Where to read next

Open Chapter 21 companion →

Read the full definitions, figures, and worked examples in Chapter 21: Fokker-Planck and Distribution Dynamics — see the mind-map node Ornstein-Uhlenbeck & Heat Equation Solutions.