New answers tagged

0 votes

Does it make sense to use batch normalization in deep (stacked) or sparse auto-encoders?

I do not see why this would not be the case. As long as you use a similar batch optimizer the same principle should apply.
  • 206
1 vote

Why is the variational lower bound is easier to compute than the original marginal distribution?

To calculate $p(x) = \int p(x|z) p(z) dz$, you have to calculate it with all configurations of $p(x|z)$ and $p(z)$, which scales exponentially with time. Thus, it is easier to estimate $p(x)$ than to ...
1 vote

How does mixing and matching encoders and decoders work in image segmentation?

It's possible to mix and match all sorts of encoders and decoders. If the output of the encoder can be mapped to the input of the decoder, and a loss function can be backpropagated through the model, ...

Top 50 recent answers are included