The ML Technique Every Founder Should Know

Introduction to Diffusion Models00:00

Francois Shaard, YC visiting partner, discusses diffusion, a fundamental machine learning framework. Background: computer vision since 2012 in Fei-Fei Li's lab, ran Focal Systems for a decade, now at Stanford finishing PhD on diffusion-based world models for AGI. Covers what diffusion is, its evolution over the past decade, and current uses.

Defining Diffusion00:31

Diffusion learns any p(data) for any domain given data. All ML models learn data distributions, but diffusion excels at mapping high dimensions to high dimensions in low-data regimes. Example: 30 images of Gary (1000x10000x3 dimensional space) to map to 3 million dimensional space with only 30 training samples.

Basic Process of Diffusion01:30

Take data sample (image of Anka or Gary), add noise repeatedly to create noised-up images. Easy to noise; hard to reverse to original data. Train model to reverse: noiser and denoiser, where denoiser is the trained model. Teach model with noised images to learn intermediate representations back to p(data).

Applications of Diffusion02:30

Roots in 2015 Joshua Susskind paper on CIFAR-10 images. Sprawls beyond: DeepMind Nobel Prize for protein folding using this procedure. Diffusion policy for driving cars. Weather prediction. Image/video generation (Stable Diffusion and newer versions). Life sciences: DiffDock for small molecule binding to proteins; newest AlphaFold uses diffusion heavily.

Evolution and Key Innovations03:31