Skip to main content

New answers tagged

0 votes

How to determine the quality of synthetic data?

Check this whitepaper that explains a ton of metrics used to measure synthetic data quality: https://ydata.ai/resources/syntheticdata-quality-metrics
Gonçalo Martins Ribeiro's user avatar
0 votes

Trying to understand some derivation in the paper: Deep Unsupervised Learning using Nonequilibrium Thermodynamics

Question 1 is indeed correct. From there, the integral for $\int dx^{(t)} q(x^{(t)}|x^{(t-1)})$ is also correct. The problem is that this expression does not appear in your intended integral. In $$\...
ThunderSmotch's user avatar
0 votes

How do Energy Based Models solve Multiple possible outputs given one input

Indeed the usual probabilistic models such as VAE whose main drawback is that samples from the model trained on images tend to be somewhat blurry possibly due to your mentioned inherent effect of ...
cinch's user avatar
  • 2,307
0 votes

How do Energy Based Models solve Multiple possible outputs given one input

think of a GAN… the discriminator is just asked if a specific $x$ works for a specific $y$, and thus you can think of the discriminator as an energy model indeed, this way, you don’t have to average ...
Alberto's user avatar
  • 1,938

Top 50 recent answers are included