score-matching
2 free lessons tagged score-matching across AI. Each one is a short sequence of focused steps with narration and a five-question quiz at the end — take them in any order, no signup required.
Training Energy-Based Models
Training an EBM means shaping an energy landscape so real data sits in valleys, but the intractable partition function blocks plain maximum likelihood. This lesson covers the push-down-push-up principle, contrastive methods (contrastive divergence, noise-contrastive estimation), score matching, and the regularized alternative that avoids sampling entirely.
Diffusion models: learning to create by learning to denoise
How diffusion models generate images and more: the forward process that destroys data with noise, the reverse process that learns to undo it, the surprisingly simple training objective, and the network backbones (U-Net, DiT) that make it work.