The Guardian is reporting that Google is trying to understand how its neural net for image recognition works by feeding in random noise then telling the neural net to look for certain features then feeding the resulting image back in. Apart from anything else some of the images generated are astounding.
Link to original Google research article.
(Score: 2) by kaszz on Saturday June 20 2015, @09:24PM
Androids don't dream. It might be running NetBSD. So computers with neural networks may have dreamlike behavior.
(Score: 5, Funny) by LoRdTAW on Sunday June 21 2015, @12:53AM
So you're saying it needs therapy to help cope with its many daemons. That is disturbing.
(Score: 2) by looorg on Saturday June 20 2015, @10:02PM
What if I put it on vibrate-mode, will the android device still enter dream-sleep?
(Score: 2) by JNCF on Saturday June 20 2015, @11:54PM
So LSD induces a recursive pattern-matching algorithm in the human brain, right? Is that what this means, guys? Is that why it seems like The Meaning of Life was hidden under that molecule, because our ape-brains just really like finding patterns in the noise?
Well shit, I was hoping it would turn out to be some sort Terence-McKenna-hoodoo-voodoo-bullshit. So it goes...
(Score: 0) by Anonymous Coward on Sunday June 21 2015, @12:36AM
I haven't taken LSD, but I have taken psilocybin, and these images look VERY familiar. I don't think it has anything to do with some kind of spiritual truth, it's just a good way of processing images. Much like other man made structures and algorithms might look a lot like things you'd find in nature.
(Score: 2) by Rich on Sunday June 21 2015, @01:36AM
To me, these images look strange in one way, but very familiar in another. I've seen similar opinions on other forums, so this might be(come) a rather interesting discovery. One thing that I have not seen mentioned yet is, that some of these look a lot like from "Iblard", a fantasy world created by Japanese artist Naohisa Inoue.
http://www.iblard.com/english/ [iblard.com]
(Score: 2) by quadrox on Sunday June 21 2015, @06:23AM
Unfortunately I don't have much to comment otherwise, but this article is pure awesome. Thanks for sharing!
(Score: 2) by fleg on Monday June 22 2015, @03:02AM
glad you liked it! :)
(Score: 2) by fritsd on Sunday June 21 2015, @12:52PM
I found it awesome as well, I'm going to try it out if I ever find the energy.
I vaguely remember how to program a backprop, and I know a little bit about the problem that an m → n dimensional mapping, with m >> n, cannot be inverted. Besides, with a sigmoid activation function, the mapping isn't even linear.
So how do you construct an (m-n) dimensional basis set to "espalier" [bbc.com] the missing dimensions?
Backprop is pretty simple to understand, maybe what these researchers found is simple as well.
The images remind me of Jeroen Bosch's painting "de Tuin der Lusten [wikipedia.org]" (might be NSFW or make you crazy). Or like when you read Mythago Wood [wikipedia.org]. Quite disturbing, really.
(Score: 2) by acid andy on Sunday June 21 2015, @07:27PM
These could be self associative neural networks e.g. Hopfield networks. I am not sure if back prop is used with those, though I'm no expert.
If a cat has kittens, does a rat have rittens, a bat bittens and a mat mittens?
(Score: 0) by Anonymous Coward on Monday June 22 2015, @03:52AM
Their algorithm sucks if it is supposed to recognize bananas but does so even if there are no bananas... I think this is just spin on a failed project.
(Score: 2) by fritsd on Monday June 22 2015, @10:55AM
Their algorithm sucks if it is supposed to recognize bananas but does so even if there are no bananas... I think this is just spin on a failed project.
Failed projects are sometimes the most interesting projects. Have you never heard about serendipity [wikipedia.org]? Like how Teflon [wikipedia.org] was invented? Tefal frying pans FTW.
(Score: 0) by Anonymous Coward on Monday June 22 2015, @07:19PM
No disagreement there. I just disagree with (the possible) obfuscation of the motivations for the project.
(Score: 2) by jasassin on Wednesday July 01 2015, @06:53AM
Wow. Some far out artwork. Thanks for the link! Very interesting.
jasassin@gmail.com GPG Key ID: 0xE6462C68A9A3DB5A
(Score: 0) by Anonymous Coward on Monday June 22 2015, @09:00PM
That's my objection to AIs done this way:
You may think you've "succeeded" but you only got X%.
You don't actually know how it works.
You don't actually know when it fails (especially for more complex ones).
You don't actually know what you're doing.
It's like the Alchemy days - where people were mixing stuff together and sometime stuff worked, sometimes stuff seemed to be promising (fool's gold). And they didn't have a good idea of what was going on.
(Score: 2) by takyon on Wednesday July 01 2015, @05:52AM
Alchemy is fun. It got funded then, and it can get funded now.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]