Linked Questions

119 votes
8 answers

How does the reparameterization trick for VAEs work and why is it important?

How does the reparameterization trick for variational autoencoders (VAE) work? Is there an intuitive and easy explanation without simplifying the underlying math? And why do we need the 'trick'?
David Dao's user avatar
  • 2,804
56 votes
6 answers

What are the main theorems in Machine (Deep) Learning?

Al Rahimi has recently given a very provocative talk in NIPS 2017 comparing current Machine Learning to Alchemy. One of his claims is that we need to get back to theoretical developments, to have ...
22 votes
4 answers

Why do we need autoencoders?

Recently, I have been studying autoencoders. If I understood correctly, an autoencoder is a neural network where the input layer is identical to the output layer. So, the neural network tries to ...
larry's user avatar
  • 321
12 votes
1 answer

Variational autoencoder with Gaussian mixture model

A variational autoencoder (VAE) provides a way of learning the probability distribution $p(x,z)$ relating an input $x$ to its latent representation $z$. In particular, the encoder $e$ maps an input $...
D.W.'s user avatar
  • 6,588
6 votes
1 answer

What's the difference between autoencoders and deep autoencoders?

I have seen the term deep autoencoders in a couple of articles such as Krizhevsky, Alex, and Geoffrey E. Hinton. "Using very deep autoencoders for content-based image retrieval." ESANN. 2011. What's ...
user156023's user avatar
2 votes
1 answer

Is Variational Inference to make an inference of conditional probability from joint probability? [closed]

While studying variational inference, I am told that it is to make an inference from conditional probability from joint probability, directly. Somehow, it is kind of hard to understand why it is so, ...
user122358's user avatar
  • 1,673
3 votes
1 answer

Improvement in NN regressor by Negative Log Liklihood loss vs MSE loss

I am trying to write a simple NN based regressor, and I have noticed that if i take two identical NN, one with mean square error loss, ane with sample drawn as gaussian prior over final output, with ...
ipcamit's user avatar
  • 217
1 vote
1 answer

Understanding reparameterization trick and training process in variational autoencoders

I am trying to understand variational autoencoders, particularly the sampling component and the reparameterization trick. I understand that instead of using a fixed determinstic latent representation ...
Jane Sully's user avatar
  • 1,010
5 votes
2 answers

VAE : How is likelihood $p(x|z)$ defined?

Disclaimer : not a strong background in Bayesian statistics. I gather from questions such as this one and this one that in the context of VAEs, we suppose that we know the (form of the ?) prior $p(z)$ ...
Soltius's user avatar
  • 1,246
2 votes
1 answer

Variational Autoencoder, understanding this diagram

I'm not an ML scientist, but I'm trying to understand how variational autoencoder works. I'll take as reference the following diagram, which it couldn't be used for backpropagation as includes a ...
user8469759's user avatar
2 votes
2 answers

Intuitive Explanation of "AutoEncoders"

To my knowledge, Autoencoders are an unsupervised learning technique in which we leverage neural networks for the task of representation learning. I know there is a lot of topics around autoencoders, ...
Thalassophile's user avatar
2 votes
1 answer

How to generate new data with a VAE?

I have built the following function which takes as input some data and runs a VAE on them: ...
quant's user avatar
  • 511