Live data from Hacker News

How much information can a small image contain?

camerongordon.site

21–30 of 30 posts

Re: How much information can a small image contain?

#21
I sort of came at the combinations of small images from a slightly different angle when I was a teenager, I was imagining that if there was a movie of your life (and everyone elses, in fact every possible life you could live) then you could produce every still image of that video if you restricted the bounds of the image to something small but understandable. I was very quickly was disappointed at how big the numbers get :)

Re: How much information can a small image contain?

#23

Many moons ago, I wondered what it would look like if you iteratively generated every possible image. It doesn't sound very useful at all (and it certainly isn't) but I learned C++ and SDL that way. This is probably terrible code by anybody's standards but maybe someone wants to take a look: https://github.com/svenstaro/infinerator

A story about the text version of this concept: https://en.wikipedia.org/wiki/The_Library_of_Babel

Check out this one too if you haven't: https://en.wikipedia.org/wiki/The_Nine_Billion_Names_of_God

Re: How much information can a small image contain?

#25

> "Machine learning tries to do by math what we are able to do by instinct" ...except that we also do it by math. It is just so fast and optimized, that we refer to it as instinct.

That's like saying gravity works because it uses math. No, we just applied our version of math to it

Re: How much information can a small image contain?

#26
post #3
post #2

The introduction has lost me completely: such a long winded way to say that 32x32x3 bytes can represent 2^(32x32x3x8) different values.

I think the point of the article is that there isn't 2^(32x32x3x8) meaningful images that can be encoded - there's far less than that because so many of the possible arrangements of the data are just meaningless noise, or millions of versions of the same thing with slightly altered color values etc. The article is saying that neural networks are cool, because part of what they do is finding which images actually cont…

I got the point quickly enough (from the title and initial table of snapshots?), but author has lost me as a reader due to saying little with too many words before they could elaborate on the point.

Re: How much information can a small image contain?

#28
Very very misleading.

First, article tried to assess information capacity in Shannon style, completely disregarding what signal is (a) two-dimensional and (b) highly redundant, that is, ignoring the traits of being an image.

Second, article taken too much liberties while mixing photorealistic and pixel-art images. The latter is really an art, since there is no formally defined ("machine") transform between these two types. And last but not least these types have significantly different information density profiles.

No DSP curiosity here.

Re: How much information can a small image contain?

#30

Many moons ago, I wondered what it would look like if you iteratively generated every possible image. It doesn't sound very useful at all (and it certainly isn't) but I learned C++ and SDL that way. This is probably terrible code by anybody's standards but maybe someone wants to take a look: https://github.com/svenstaro/infinerator

A story about the text version of this concept: https://en.wikipedia.org/wiki/The_Library_of_Babel

An an online version based on that story: https://libraryofbabel.info/
Post reply on HN