Blade Runner re-encoded using neural networks

Re:Blade Runner re-encoded using neural networks by klakier on Friday June 03, 2016 @08:47AM (#11829993)

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: nothing impressive here.

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by zodiac on Friday June 03, 2016 @10:20AM (#11830437)

> 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.

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by kastnerkyle on Friday June 03, 2016 @05:27PM (#11833392)

Note that DCGAN (or standard GAN generally) doesn't have an encode path (or any other way to easily condition generation) so it is not well suited to this particular task. The image quality is stellar though, and I linked to several recent papers above which combine a GAN approach with an explicit encode. This should allow them to be used for the kinds of things in this link.

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by klakier on Friday June 03, 2016 @11:17AM (#11830798)

Thanks for great answer!

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by sp332 on Friday June 03, 2016 @10:23AM (#11830453)

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.

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by l3m0ndr0p on Friday June 03, 2016 @09:28AM (#11830172)

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.

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by Mithaldu on Friday June 03, 2016 @09:31AM (#11830180)

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

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by l3m0ndr0p on Friday June 03, 2016 @09:51AM (#11830277)

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

[ Parent | on HN ]

Re:Blade Runner re-encoded using neural networks by tacos on Friday June 03, 2016 @09:56AM (#11830303)

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

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

[ Parent | on HN ]