Data & representations · Glossary term

What is Latent Space?

A learned representation space whose coordinates encode factors useful to a model. It may be lower-dimensional than the input, but compression is not required for every latent representation.

What people say

“A model's hidden representation space.”

What is the common confusion about Latent Space?

Nearby points are only meaningfully similar according to what the model and training objective learned.

Learn Latent Space in the course

Lessons that name Latent Space in a title or section

  • Stable Diffusion — Architecture & Fine-Tuning

    Stable Diffusion is a DDPM that runs in the latent space of a pretrained VAE, conditioned on text via cross-attention, sampled with a fast deterministic ODE solver, and steered by classifier-free…

    Phase 04: Computer Vision

Covered in Phase 04: Computer Vision.

  • EmbeddingA learned mapping from discrete items (words, images, users) to dense vectors in continuous space, where similar items end up close together
  • VAE (Variational Autoencoder)A latent-variable model trained with a reconstruction objective and a regularization term that keeps an approximate posterior close to a…
  • FeatureAn individual measurable property of the data. In classical ML, you engineer features by hand.
  • Diffusion ModelA generative model trained around a progressive noising process and a learned reverse process.
  • EigenvalueA scalar that describes how a linear transformation scales a corresponding nonzero eigenvector without changing its direction.
  • GAN (Generative Adversarial Network)A generator network tries to create realistic data while a discriminator network tries to tell real from fake.

More terms in Data & representations

Open the Data & representations list in the glossary

This entry comes from glossary/terms.md on GitHub. Browse all 250 glossary terms.