Blade Runner re-encoded using neural networks • Hacker News Board

Re: Blade Runner re-encoded using neural networks

#31

Post by amelius » Fri, Jun 03, 2016, 1:42 PM UTC

robert_tweed wrote: post #27

svantana wrote: post #23

This article alludes to, but never actually brings up, something much more interesting than the project in question: How can copyright coexist with human-level automatic analysis and synthesis of works of art? For example, Spotify is flooded with "covers" of hit songs that are made to sound as similar to the original as possible. In my understanding, it doesn't matter how similar it sounds, as long as it's "remade",…

I'm pretty sure the law as it stands is robust enough to deal with these issues on the basis of similarity vs substantive difference. A cover usually sounds quite different to an original, enough so that a fan would certainly not consider them the same thing. OTOH, simply using some well recognised phrases (not necessarily a sample) can infringe on the mechanical rights, which are the copyright on the composition as…

So then the algorithm for creating a cover should include a way to detect whether the song is still within the sphere of similarity. This could be used, for example, to iteratively come to a point where the song is no longer considered similar.

Re: Blade Runner re-encoded using neural networks

#32

Post by l3m0ndr0p » Fri, Jun 03, 2016, 1:51 PM UTC

Mithaldu wrote: post #30

l3m0ndr0p wrote: post #29

Earlier quoted context omitted.

I agree. I was wondering why this is such a big deal. When a "neural networking" computer has a flash of inspiration and creates a screen play for a movie, and creates a virtual world based on that screen play. Then we'll have a something to talk about.

See my explanation for why this matters here: https://news.ycombinator.com/item?id=11830140

OH. Thank you. Now that makes a bit more sense & it's looks like an impressive feat for data compression.

Re: Blade Runner re-encoded using neural networks

#33

Post by tacos » Fri, Jun 03, 2016, 1:56 PM UTC

Mithaldu wrote: post #30

l3m0ndr0p wrote: post #29

Earlier quoted context omitted.

I agree. I was wondering why this is such a big deal. When a "neural networking" computer has a flash of inspiration and creates a screen play for a movie, and creates a virtual world based on that screen play. Then we'll have a something to talk about.

See my explanation for why this matters here: https://news.ycombinator.com/item?id=11830140

An explanation written by someone who actually did it a decade ago:

https://www.quora.com/What-is-the-potential-of-neural-networ...

Re: Blade Runner re-encoded using neural networks

#34

Post by usrusr » Fri, Jun 03, 2016, 2:09 PM UTC

buro9 wrote: post #25

svantana wrote: post #23

This article alludes to, but never actually brings up, something much more interesting than the project in question: How can copyright coexist with human-level automatic analysis and synthesis of works of art? For example, Spotify is flooded with "covers" of hit songs that are made to sound as similar to the original as possible. In my understanding, it doesn't matter how similar it sounds, as long as it's "remade",…

Music has that sorted already. There is copyright. There is publishing right. If you make a cover of a recording, it is the latter that you are involved with. You'd have to go to the publishers of a piece of music to license the right to publish your interpretation of the work. Obviously this post simplifies, but it's already answered.

Corner case: Neil Innes' songs for The Rutles. They are so clearly not covers yet so perfectly recognizable.

Re: Blade Runner re-encoded using neural networks

#35

Post by zodiac » Fri, Jun 03, 2016, 2:20 PM UTC

klakier wrote: post #24

Bullshit... this is still encoding. It does not matter that it is using neural network to encode frame. Guys, when you get over this neural network hype? I can as well create and encoder using some machine learning, to create a blurry and inferior version of the movie. But what's the point? I could as well used other prediction method with some kind of memory, much superior and nobody will enjoy it. Summing up: nothi…

> But what's the point?

Autoencoders don't really have much practical use now, but that's not the point of them. The point is we really want to figure out how to do unsupervised learning well and autoencoders are one of the few ways of doing it.

We want to do unsupervised learning well because most learning that humans do is unsupervised.

The idea behind autoencoding is that by forcing the network to try to learn efficient ways to compress the data, it could learn important features of the data. The fact that the pictures are so blurry means that this doesn't work very well, but that's why it's a research problem.

Autoencoders don't work well, but some unsupervised techniques that extend on them do, and we get impressive results like https://arxiv.org/pdf/1511.06434.pdf (see page 5) where the network learns to generate natural-looking bedroom images.

Re: Blade Runner re-encoded using neural networks

#36

Post by zodiac » Fri, Jun 03, 2016, 2:22 PM UTC

dogma1138 wrote: post #3

Can anyone explain what does this encoder actually does and how is it different than any other encoder? The article almost seems to make it sound that this encoder somehow reconstructed the film...

It applies the unsupervised learning technique of https://en.wikipedia.org/wiki/Autoencoder

As for why it's important and not just another encoder like mpeg4, see my response at https://news.ycombinator.com/item?id=11830437

Re: Blade Runner re-encoded using neural networks

#37

Post by sp332 » Fri, Jun 03, 2016, 2:23 PM UTC

klakier wrote: post #24

Bullshit... this is still encoding. It does not matter that it is using neural network to encode frame. Guys, when you get over this neural network hype? I can as well create and encoder using some machine learning, to create a blurry and inferior version of the movie. But what's the point? I could as well used other prediction method with some kind of memory, much superior and nobody will enjoy it. Summing up: nothi…

The author's own blog https://medium.com/@Terrybroad/autoencoding-blade-runner-889... makes it clearer that this is primarily an art project. It's supposed to make you think about how minds understand things, not to be a superior encoder.

Re: Blade Runner re-encoded using neural networks

#38

Post by kastnerkyle » Fri, Jun 03, 2016, 2:23 PM UTC

vintermann wrote: post #19

kastnerkyle wrote: post #12

Earlier quoted context omitted.

Yes, although the particular technique used here (variational autoencoder, or VAE) doesn't benefit from increasing the code space due to a particular penalty (KL divergence against a fixed N(0, 1) Gaussian prior) during training. So even by making it go to 1000 digits in the code space, the model will probably still only choose to use 5 or 10 dimensions unless the KL penalty is relaxed, making it closer to a standard…

Given that Adversarially Learned Inference came out yesterday , the best approach may be to just wait a couple of months and see what the state of the art is then.

Sure - that is always an option especially in deep learning right now. But this current crop of models (counting in DCGAN and LAPGAN/Eyescream) has really made a leap in my eyes from before "oh cool generative model" to "are these thumbnails real?". They are really generating a lot of cohesive global structure, which is pretty awesome!

Re: Blade Runner re-encoded using neural networks

#39

Post by stefs » Fri, Jun 03, 2016, 2:25 PM UTC

annalewiss wrote: post #21

These complexities and nuances of sci-fi culture and artificial learning were quite possibly lost on whoever decided to file the takedown claim for Warner Bros.

> whoever decided to file the takedown

maybe that was a bot, which would add another layer to the story.

Re: Blade Runner re-encoded using neural networks

#40

Post by radarsat1 » Fri, Jun 03, 2016, 2:35 PM UTC

Mithaldu wrote: post #28

dogma1138 wrote: post #3

Can anyone explain what does this encoder actually does and how is it different than any other encoder? The article almost seems to make it sound that this encoder somehow reconstructed the film...

This is possibly the next generation of video/audio/image codecs. What he did was create a specialized compression algorithm that works very well to compress the data that is each frame of Blade Runner, and decompress it (lossily, like mp3) back into a video stream. To put this into perspective: Blade Runner is 117 minutes long. At 25 frames per second, that is 175_500 frames. As he says, the input data he used was 2…

Except that in my understand, the decoded version looks like shit. So, while optimistic that this technology might be quite good eventually, more heuristics are probably needed for the right way to extract an optimal encoding.

e.g. see the screenshots here:

http://www.eteknix.com/blade-runner-gets-trippy-auto-encoded...