什么叫CD(Contrastive Divergence)-k

Two tricks to speed up the sampling process:
-1-: Since we want P(v)~Ptrain(v), we initialize the Markov chain with a training example (instead of random initialization)
-2-: Does not wait for the chain to converge. Samples are obtained only after k-steps of Gibbs sampling.

发表评论

电子邮件地址不会被公开。 必填项已用 * 标注

*

您可以使用这些 HTML 标签和属性: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <strike> <strong>