Part 2 Lesson 12 wiki

Can GANs be used for data augmentation?

7 Likes

A way to detect naiive copying in GANs is to find similar images in the CNN feature space.
This was done by somebody on the famous nvidia progressive GAN (with faces).

Edit:
found the link:

7 Likes

They are actually pretty cool … as abstract art.

1 Like

no, it gets closer to “jeremy’s” only after 75-100 epoch

1 Like

@emilmelnikov Mondrian

Any GANS for music?

2 Likes

Here is Helena’s twitter

12 Likes

A side note:

This is a paper that gets crazy good results (not really based on GANS) that I tried to implement.

My implementation (poorer quality results) :

2 Likes

RNNs works better for sequential data than GANS:

There is also Wavenets which also work great on sequential data generation.

4 Likes

@Interogativ See Project Magenta from Google https://magenta.tensorflow.org/

2 Likes

All of this sounds awfully like translating in one language to another then back to the original. Have GANs or any equivalent been tried in translation?

5 Likes

I was just thinking the same thing. It’s an interesting idea for sure.

How to implement a GAN for a time-series model ? I’m not able to wrap my mind around it.

almost exactly what you mentioned:

Unsupervised Machine Translation Using Monolingual Corpora Only

(shameless plug)
my summary on that paper:

12 Likes

Thanks!

Can anyone share the deeplearning.net link of the gif/interactive diagram or diagram Jeremy showed earlier (couldn’t find it?)

please briefly explain vae, compared with gan’s?

http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html

2 Likes

That paper looks awesome. Thanks for sharing.

Thx I forgot to scroll lol.