How to pronounce“autoenccoder”in English

autoenccoders which is I view them as a subclass of Helholds machines.

autoenccoders, right? And we know how to deal with autoenccoders.

variational autoenccoders something that's been uh quite uh there's been a lot of development in our community in deep learning community in that space

nonlinear autoenccoders. Um and you can sort of pre-train these models using restricted bulk machines or autoenccoders uh

um uh using autoenccoders.

component analysis model autoenccoders and such uh and again you can sort of say well every single image is made up by some some linear combination of these

convolutional deconvolutional variational autoenccoders which is again convolutional deconvolutional autoenccoders just with with some noise and you can certainly see that you know

bit more closer to an autoenccoder.

Um about the v version autoenccoder uh for the more challenging data set

models like sparse coding uh autoenccoders uh clustering based methods uh and these are all very very powerful uh powerful techniques and I'll

and that sort of flows naturally into the ideas of autoenccoders right the autoenccoder is a general framework where you if I give you an input data

now if you were using a deterministic system like an autoenccoder you would generate one image right because it's a deterministic system give an input I

gang can generate clearer image than the variational autoenccoder.

prop or if you want to do variational autoenccoders you have to introduce a reparameterization layer and you have to append an additional small loss that

So theta here will denote the parameters of the variational autoenccoders.

generally and then you know you can stitch them together into this deep autoenccoder and back propagate through uh reconstruction loss.

is just a change sequence of variational autoenccoders and there's a recognition model which is you can think of it as deterministic system like a

are saying that they can actually generate really nice looking images using variational autoenccoders.

You can use something that's called an autoenccoder um just multiple levels.

Um uh but again this is just a way uh typically autoenccoder is a way of compression or or trying to do

know empirically the statistics between the data and the model right very similar to what the autoenccoder is doing but slight slight differences and

If you wanted to do autoenccoders so you want to do some unsurprised learning or something like that.

There is an interesting uh sort of relationship between autoenccoders and pro and principal component analysis.

doing PCA which is sort of a nice uh uh uh connection because it basically says that autoenccoders you can think of them as nonlinear extensions of PCA, right?

know what I think that one of the problems with image generation today is that with variational autoenccoders there is this notion of Gaussian loss

So that would be a autoenccoder you again have an L2 loss at the end and you back

So what is a variational autoenccoder?

It's a deterministic system and you can think of this thing inside is just an autoenccoder