[danielbigham]

I have a suspicion that in the future computers will use a vaguely DNN-like approach for compression, but I haven't seen any super compelling examples of this yet. I can say "imagine a photo taken at 2000 feet and 2 miles away of the Eifel Tower with a beautiful orange sunset in the background", and your mind can use it's internal representation to render something along those lines. I feel like computers some day should be able to do the same thing, except that with another kilobyte of constraints I should be able to make the final result really close to a particular photo that matches that description.

[anonfunction]

Though it has little bearing on your point, many people including myself do not possess the ability to "imagine a photo". It is known as aphantasia and Blake Ross has a great article[1] on the subject.

1. https://www.facebook.com/notes/blake-ross/aphantasia-how-it-...

[exikyut]

Well, in an even more distant future, a more developed version of the kind of neural networks that the GP describes could be hooked up to your brain to provide this functionality.

[arnioxux]

There was another submission recently that kind of does what you described. Click on the visualizations to see the iterations: https://dmitryulyanov.github.io/deep_image_prior. The ELI5 is that prior knowledge of what images look like can be used to reconstruct images w/o corruption.

For non-images, this idea is pretty old and sounds a lot like compression algorithms that share a pre-defined dictionary. For example: https://en.wikipedia.org/wiki/Brotli, "improved the compression ratio by using a pre-defined dictionary of frequently-used words and phrases." Of course words/phrases are a lot easier to predefine.

I wonder how large the predefined weights of the NN has to be to effectively compress real world images?