Algorithm Search⌘K

Algorithmadvanced

Contrastive divergence

Also called CD-k.

Approximates the gradient of the log-likelihood of energy-based models by a few Gibbs sampling steps; used to train RBMs.

Approximates the gradient of the log-likelihood of energy-based models by a few Gibbs sampling steps; used to train RBMs.

About this page

The build computes these levels from the evidence in the repository. Each row says what the next level needs. Read what the levels mean.

LadderLevelWhat the next level needs
Human proofH0 no proof
  • add a proof in proofs/ (06.5)
LeanL0 no Lean part
  • name a Lean module in the lean field (07)
VisualV0 none
  • add viz/scene.ts or a figure (10)
WritingW0 stub
  • the section The problem
  • pseudocode in The algorithm
  • complexity claims in the front matter
  • one source with a locator

Tag ZQSFAJ Edit this page History Report an error