Index Ai Academy
Glossary · Phase 5 · Transformers

Forward process

The fixed formula in a diffusion model that adds a little noise to data at each step until only noise is left.

Try it now

Press Next through the steps 1, 10, 25, 50 and 100.

Learn it properly

Diffusion 1: turning data into noise · The easy half of a diffusion model: one step of noise, why the data is shrunk as noise is added, the jump to any step with alpha bar, how to read a noise schedule, and the training examples a denoiser learns from. About 40 minutes.

Other terms from the same lesson

  • diffusion model: A generative model that learns to undo small steps of added noise, and makes new data by starting from pure noise and removing it step by step.
  • noise schedule: The list of betas in a diffusion model, one per step, saying how much of each step is noise.
  • reverse process: The learned half of a diffusion model: a network that undoes one small step of noise, run many times starting from pure noise.
Keep learning

More in plain English.

1286 terms in the glossary, each with the lesson that teaches it.

1286 terms

The glossary

Every word you'll meet in AI and machine learning, explained in everyday language.

Phase 5 · lesson 40 min

Diffusion 1: turning data into noise

The easy half of a diffusion model: one step of noise, why the data is shrunk as noise is added, the jump to any step with alpha bar, how to read a noise schedule, and the training examples a denoiser learns from.

Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write