5,337
edits
Visual Learning and Recognition: Difference between revisions
Visual Learning and Recognition (view source)
Revision as of 18:50, 1 December 2020
, 1 December 2020→Variational Auto-encoders (VAEs)
| Line 1,150: | Line 1,150: | ||
<math> | <math> | ||
\begin{aligned} | \begin{aligned} | ||
\log P(x) - D_{KL}[Q(z|x) \Vert P(z|x)] = E_{z \sim Q}[\log P(x|z)] - D_{KL}[Q(z|x) \Vert P(z)]\\ | &\log P(x) - D_{KL}[Q(z|x) \Vert P(z|x)] = E_{z \sim Q}[\log P(x|z)] - D_{KL}[Q(z|x) \Vert P(z)]\\ | ||
\implies \log P(x) \geq E_{z \sim Q}[\log P(x|z)] - D_{KL}[Q(z|x) \Vert P(z)] | \implies &\log P(x) \geq E_{z \sim Q}[\log P(x|z)] - D_{KL}[Q(z|x) \Vert P(z)] | ||
\end{aligned} | \end{aligned} | ||
</math> | </math> | ||