Slashdot Mirror

← Back to Stories (view on slashdot.org)

Turning Neural Networks Upside Down Produces Psychedelic Visuals

Posted by Soulskill on from the not-literally-upside-down dept.

cjellibebi writes: Neural networks that were designed to recognize images also hold some interesting capabilities for generating them. If you run them backwards, they turn out to be capable of enhancing existing images to resemble the images they were meant to try and recognize. The results are pretty trippy. A Google Research blog post explains the research in great detail. There are pictures, and even a video. The Guardian has a digested article for the less tech-savvy.

75 comments

  1. They've nailed it by DavidSpencer · · Score: 5, Informative

    I've had a few up-close experiences with heavy psychedelics. Those photos took me right back. Wonderful insights!

    1. Re:They've nailed it by Anonymous Coward · · Score: 0

      Do you think it's a good idea to admit a crime in public especially given you use your real name?

    2. Re:They've nailed it by Anonymous Coward · · Score: 3, Interesting

      That makes an argument as to what psychedelics actually do.

    3. Re:They've nailed it by secretsquirel · · Score: 0

      AC took teh blue pill

    4. Re:They've nailed it by qpqp · · Score: 4, Insightful

      While I agree that the photos provoke a similar reaction on a superficial glance, what struck me while on psychedelics was the actual texture of what you see, which extends fractal-wise when concentrated upon.

    5. Re:They've nailed it by Livius · · Score: 2

      It's a crime to be a test subject for experimental pharmaceuticals?

    6. Re:They've nailed it by Anonymous Coward · · Score: 0

      It's a crime to be a test subject for experimental pharmaceuticals?

      Yes it is a crime, if you don't have FDA approval to do so. Can't just go experimentin' with your own pharma in the good ol' USA. Not that it stops people from doing so less than legally...

    7. Re:They've nailed it by iMadeGhostzilla · · Score: 3, Interesting

      It's true. And we know the physical texture does extend fractal-wise into infinity... I'm thinking the opposite is when one is not on psychedelics and is further stressed out, texture details disappear if they are not relevant for the stressful situation. (E.g a sponge becomes a yellow block, no holes or pores.) As if psychedelics open the valve and stress closes it, like many people have said.

    8. Re:They've nailed it by Anonymous Coward · · Score: 0

      I've theorized that when you are looking for something, you picture what you expect to see and match it against the data your eyes are sending you. That's why it's more difficult to find something if you've never seen it before. For example, someone says "hand me the pipe wrench from my toolbox" and you don't know what colour it is, what size it is, etc. that's harder to find. Once you know what it looks like, it's easy.

    9. Re:They've nailed it by Anonymous Coward · · Score: 0

      If only Dr Shulgin were alive today I reckon he would be most interested in this article. I am amazed how similar some of the images look to my experiences with 2CB.

    10. Re:They've nailed it by spongman · · Score: 1

      > up-close experiences with heavy psychedelics

      yuk, i try to steer clear of obese mystics.

    11. Re:They've nailed it by Jane+Q.+Public · · Score: 1

      If all OP got out of that was that layers of neural nets make cool pictures...

      WHY the hell is it on Slashdot?

    12. Re:They've nailed it by cjellibebi · · Score: 2

      Because reverse-engineering psychedelics is news for nerds.

    13. Re:They've nailed it by narcc · · Score: 1

      That's ... not even close to what they did.

      --
      Required reading for internet skeptics
    14. Re:They've nailed it by Anonymous Coward · · Score: 0

      That makes an argument as to what psychedelics actually do.

      Gives another meaning to "Brain Vomiting".

    15. Re:They've nailed it by Anonymous Coward · · Score: 0

      I've theorized that when you are looking for something, you picture what you expect to see and match it against the data your eyes are sending you. That's why it's more difficult to find something if you've never seen it before. For example, someone says "hand me the pipe wrench from my toolbox" and you don't know what colour it is, what size it is, etc. that's harder to find. Once you know what it looks like, it's easy.

      You're saying it's all about the greebles eh? Or is that just what the matrix is telling your brain to think?

    16. Re:They've nailed it by cjellibebi · · Score: 1

      But it could have great implications in the ongoing quest to reverse engineer the psychedelic experience on a purely intellectual level.

    17. Re:They've nailed it by narcc · · Score: 1

      No, no it couldn't. It's pretty clear from the article that the summary is complete nonsense. They don't run them backwards (whatever that's supposed to mean) nor do the NN's produce images.
      .
      In the case of the random input image, as an analogy, think of the NN as a fitness function in a genetic algorithm. The photo input images work similarly.

      It makes pretty pictures, but as far as psychedelic experiences are concerned, there is absolutely no knowledge to be gained here.

      --
      Required reading for internet skeptics
    18. Re:They've nailed it by Jane+Q.+Public · · Score: 1

      Alas, Tennant's writings about baloney also contain their fair share of baloney.

      For example, he dismisses the idea that ad hominem includes the case where one party tries to discredit the other party, thereby attempting to undermine the credibility of his argument. It isn't direct ad-hominem, as a direct part of the first party's argument, but it is still an indirect attempt to undermine the second party's argument, and therefore part of the first party's argument.

      So since it is part of the first party's argument in debate, and its intent is to weaken the credibility of the second party's argument, it's no less ad-hominem even though it's indirect. Denying that is like saying the car can't have moved when 5 guys pushed it, because they didn't use the engine.

      Tennant is also correct, though, that some examples in RationalWiki are so lame as to border on false examples.

  2. I tried this myself by Anonymous Coward · · Score: 4, Funny

    I ran slashdot backwards through the DICE marketing bullshit neural network and got www.soylentnews.org

    1. Re:I tried this myself by Sowelu · · Score: 1

      So it's attractive but ultimately derivative with no new content except what you ascribe to it?

    2. Re:I tried this myself by Anonymous Coward · · Score: 0

      That's life!

  3. oot, ti deirt i by turkeydance · · Score: 1

    .dekrow

  4. Now THAT's art! by Marc_Hawke · · Score: 1

    Some of those pictures are just noise, but some of them are brilliant.

    Also, I'll go so far as to say it's not something human could do. Sure a human can do 'similar' things, but I'm betting some of the patterns are more precise than that. (For a 'barely related' but spiritually equivalent example....a human couldn't draw an actual Mandlebrot set.)

    --
    --Welcome to the Realm of the Hawke--
    1. Re:Now THAT's art! by captnjohnny1618 · · Score: 5, Informative

      A human can't do it? Alex Gray begs to differ.

      I guess we could argue that it's "similar" (i.e. not the same), but it's pretty darn close ;-).

      The Mandelbrot set is a very different animal from what these algorithms are doing. I agree that a human couldn't draw a Mandlebrot set, but in some sense this work is much less precise and analytic than something like a Mandlebrot set.

    2. Re:Now THAT's art! by Anonymous Coward · · Score: 1

      Wow, they trained a computer to apply random amounts of Photoshop filters onto existing images. I suppose any 12 year old with a Tumblr account couldn't do that.

    3. Re:Now THAT's art! by Anonymous Coward · · Score: 0

      Mandelbaum! Mandelbaum! Mandelbaum!

    4. Re:Now THAT's art! by qpqp · · Score: 1

      Wow, they trained a computer

      If they actually did that they'd have an artificial intelligence, but maybe I just overheard the "whoosh!"

    5. Re:Now THAT's art! by Tatarize · · Score: 1

      I've seen things in the clouds before. I've also heard people wax poetic about how it's a uniquely human thing.

      --

      It is no longer uncommon to be uncommon.
    6. Re:Now THAT's art! by Anonymous Coward · · Score: 0

      I agree that a human couldn't draw a Mandlebrot set [...]

      Well, it seems you'd be wrong...

      http://classes.yale.edu/fractals/mandelset/mandelmonk/mandelmonk.html

    7. Re:Now THAT's art! by captnjohnny1618 · · Score: 1

      You almost had me:

      https://en.wikipedia.org/wiki/...

    8. Re:Now THAT's art! by narcc · · Score: 1

      Some people seem to have some strange ideas about what is being done here. The reality is far less interesting:

      Say you want to know what sort of image would result in “Banana.” Start with an image full of random noise, then gradually tweak the image towards what the neural net considers a banana [...] By itself, that doesn’t work very well, but it does if we impose a prior constraint that the image should have similar statistics to natural images, such as neighboring pixels needing to be correlated.

      Even less exciting, naturally, are the swirly ones and the ones with the mixed images. (I presume the anthropomorphism in the quote is to tickle the Kurzweil nuts and "science" reporters.) Very few difference, but it makes prettier pictures -- start with a photo instead of noise, tweak it differently.

      In this case we simply feed the network an arbitrary image or photo and let the network analyze the picture. We then pick a layer and ask the network to enhance whatever it detected. Each layer of the network deals with features at a different level of abstraction, so the complexity of features we generate depends on which layer we choose to enhance. For example, lower layers tend to produce strokes or simple ornament-like patterns, because those layers are sensitive to basic features such as edges and their orientations.

      Don't read the comments after reading the article. You'll lose all faith in humanity.

      Next up: The amazing Markov chain AI that composes incredible music!

      --
      Required reading for internet skeptics
    9. Re:Now THAT's art! by Anonymous Coward · · Score: 0

      yeah... it is one of a few concepts for **creative machines** in AI; once you have the data partially fit, see what the structure can produce with such data. - djb

    10. Re:Now THAT's art! by Muad'Dave · · Score: 1

      Alex Gray ...

      Wasn't that the smart parrot?

      --
      Tiller's Rule: Never use a word in written form that you've only heard and never read. You will end up looking foolish.
  5. Wow! by nospam007 · · Score: 4, Funny

    The slashdot UI produces psychedelic visuals even without any artificial or natural intelligence.
    Every time I come here, there are icons all over the place, in the middle of the text, the title bar shows random icons or text and I'm not even on beta.
    Not to mention the dupes or stupid articles and don't make me begin about the videos.

    1. Re:Wow! by Anonymous Coward · · Score: 0

      not to mention the disappearing link to comments on the front page. Who the fuck goes to slashdot for the stories? this shit is all old. This place is all about the comments. Why do they have to keep fucking with it???????

  6. Amazing, need to compare after more training by turp182 · · Score: 1

    They should train the network more and see how it changes these outputs.

    Or, start out with a new network and see how things change as it becomes more competent.

    This is awesome.

    --
    BlameBillCosby.com
    1. Re:Amazing, need to compare after more training by ShanghaiBill · · Score: 1

      They should train the network more and see how it changes these outputs.

      Training it more on the same data would make little difference. You would need to train it with different images. Most image recognition using deep learning is done using layered RBMs. You actually train an RBM by shoving data through it backwards, to get it roughly working, and then fine tune it with backpropagation.

  7. Questions by wonkey_monkey · · Score: 1

    Some questions, in case anyone here knows:

    What kind of size are these neural nets, typically? As in how many bytes would it take to define one?

    I vaguely get the idea of neural nets, but how do you apply them to images (or vice versa, rather)? Does the input layer consist of one "neuron" per pixel, or what?

    --
    systemd is Roko's Basilisk.
    1. Re:Questions by sleepypsycho · · Score: 1

      Here is my best answer. I am not active in the field so the answer is a combination of knowledge, extrapolation and intuition. I think it provides some of the kind of info you are curious about

      Typically the first layer of nodes will receive input feature detectors run on the image. For example edge sharpness and orientation calculation. This will be at a range of scales that are small compared to the overall picture.

      This first layer will connect and provided weighted values to another layer or two that is also probably spatially restricted in range

      You would not actually need to have so many independent low level nodes because you can run pieces of the image be the low level node and then rout the output to the next aggregating layer.

      On aspect of deep learning is that you would train input nodes based on the final output [or at least high level nodes] rather than back propagating through all the layers. This improves the results and simplifies the interaction, allowing for more nodes to be implemented due to reduce computing time

      I tried to google for some practical values, but did not see anything that offered up number just guidelines. I am now quite curious about the value and will have to spend more than 15 minutes searching. If someone has some practical experience and some typical values, I would certainly be interested in the answer. A will now hazard a complete guess. For each 40x40 pixel square I would imaging roughly a hundred of two feature values going into the first layer of nodes on a one to one bases. I would imagine 3 to 5 intermediately layers that tapered down more minimally over the next 2 layers and then more dramatically as it goes to the final layer. This ends up with a ball park calculation for a 2000x2000 image of 2,500 patches [obviously they are overlapping areas but good enough for the estimation] and a first layer 500,000 nodes x 3 for 5 layers of reduced count to get 1.5 million nodes. I am confident that I am within 4 orders of magnitude with this guess.

    2. Re:Questions by ShanghaiBill · · Score: 3, Interesting

      I know nothing about these NNs, but the NNs used for the ImageNet Competition typically have a few hundred thousand neurons. This is to place images of about 1M pixels into one of 1000 categories. Most image recognition NNs are "convolutional" which means they are tiled. So each neuron in the first layer is only looking at a small part of the image. Later layers will pool the results from the convolutional layer into extended features. This cuts way down on both the size, and the amount of computation needed. The number of layers will typically be 5 or 6. Even more layers should, in theory, help, but deeper networks are very hard to train. The total size in bytes would be maybe 100MB, but that will vary widely depending on the implementation. I don't know how big Baidu's implementation was (they were the winner, but they cheated). NNs can run fast, categorizing hundreds or thousands of images per second. But it can take a long time to train them, days or weeks on a GPU farm. Fortunately the training is highly parallel.

    3. Re:Questions by sleepypsycho · · Score: 1

      Thanks. That is great info. I am happy about my guess. I may be only an order of magnitude off on the # of nodes and I had 5-7 layers [input, 3-5, output] :)

      When I was in college the 100 astrophysics class [rocks in space] taught estimation and actually asked how many trees in Chicago on the final. I thought this was probably one of the most valuable things you could teach liberal art students in a science class. One of my co-worker did very well on his hiring interview by doing a very good estimation of the number of veterinarians in NYC. He googled it when it he got home and was able to send a link that was about 10% from his answer. He was cherry picking, sure, but we were highly impressed. He is one of the most successful hires we ever made.

  8. Statute of limitations by tepples · · Score: 1

    I don't know about other states, but this page claims that the statute of limitations for a misdemeanor in Indiana is two years.

  9. Is this your brain on drugs? by jscottk · · Score: 5, Insightful

    This makes me wonder if a similar process is occurring in the brain of someone on a psychedelic. Are the compounds stimulating pattern recognition feedback loops from the inside out, causing people to see their imaginations manifested in the fuzz?

    1. Re:Is this your brain on drugs? by vix86 · · Score: 4, Interesting

      There is a guy that wrote wrote an essay some years ago that suggested as much. He posited that drugs like psilocibin basically overload the brain and cause it to form feedback loops. Many of the effects you can experience on hallucinogens also suggest as much. Closed eye visuals for instance are basically the "lights" you see when you push on your eye balls. They are just amplified and put into a feedback loop. Thought loops are common on hallucinogens as well, I imagine its the result of that as well.

    2. Re:Is this your brain on drugs? by Tatarize · · Score: 2

      It's likely the Convolutional neural network algorithm.

      https://en.wikipedia.org/wiki/...

      It's along well enough that you can get premade ones to invent magic the gathering cards or recognize dogs and highly dog like things in pictures. It's useful even completely independently of the AI research as such.

      --

      It is no longer uncommon to be uncommon.
    3. Re:Is this your brain on drugs? by sound+vision · · Score: 1

      That's pretty much exactly what people have been saying they do for the past 40-50 years, if not longer. I've tripped on several different psychedelics and these pictures are uncannily close to the effect... so ridiculously close that my jaw just kinda dropped when I saw it.

    4. Re:Is this your brain on drugs? by lucien86 · · Score: 1

      Yes sort of, but the brain is a heck of a lot more complicated than that. I think a lot of the psychedelic effects are caused by the 'synchroniser' and other top level filters in our visual systems shutting down allowing us to see some of how our brains actually generate our view of the world. The brain has at least two completely separate visual processing cores - one for real time motion and danger intercept and a far more complex colour vision world and object interpretation system. There is probably a third for more abstract processing and visual imagination and 3D interpretation.. A fourth interrelated subsystem does image feedback, short term visual memory, and overall control.
      Most of vision isn't actually done in real time because the brain isn't fast enough, and that synchroniser puts all the disparate pieces together into a single seamless whole... so yes psychedelic images are partly feedback but its all part of a much more complicated machine than any current artificial neural network.

      Brains are not even constructed using the same kinds of learning/tuning algorithms as neural networks and we don't really know a lot about how that part of the brain works - which is the real limit on NN's of course. I work in Strong AI and the model I am working on assumes that the brain uses a complex mathematical crib, but that is an area for future research....

      --
      Below the speed of light Special Relativity is one of the most accurate theories in physics - above the speed of light..
  10. Prints by lq_x_pl · · Score: 4, Interesting

    Any possibility that they will release higher-res versions of these images? Maybe sell some prints?
    I realize these are just the output of a funnel-run-backwards, but they'd make awfully cool posters.

    --
    An internal system operation returned the error "The operation completed successfully.".
    1. Re:Prints by JimMcc · · Score: 1

      I was wondering the same thing. I don't know if I'd want the dreamscape images or more disturbing images. Both make me stop and think about the image.

  11. not even close by Anonymous Coward · · Score: 0

    I have had a lot of LSD/LSA/MDA/MDMA/DOB/2CE/2CI/DMT and those photos do NOT look anything like what you see when tripping, anyone who says otherwise is lying.

    It's just like Hollywood films, I have never seen a drug trip in a film that looked anything like the real deal.

    1. Re:not even close by qpqp · · Score: 1

      those photos do NOT look anything like what you see when tripping

      Of course. If the dose is high enough, these pictures only look similar to the onset of a trip.

    2. Re:not even close by Anonymous Coward · · Score: 2, Interesting

      I have seen things very similar to these on some level. My pattern-recognition algorithms aren't fixated on dogs, but the way some of these images look is very familiar. Translucent objects popping out of feedback-looped noise is real. Fractal-repeated infinite patterns are real. Sky turning into crinkly paint swirls is real. Empty space around objects (like the Google logo) showing iridescent patterns is real. Now, there is a caveat that each experience I've had was as different from the previous one as it was from the default world. I also know people whose experiences are vastly different from mine, or even completely non-visual. Not all brains are wired the same!

    3. Re:not even close by Anonymous Coward · · Score: 0

      Try DOI. Then you'll think the pictures are accurate.

  12. 6 blind men analyze an elephant by D4C5CE · · Score: 1
    http://cdn2.hubspot.net/hub/13...

    TFA: The results are intriguing—even a relatively simple neural network can be used to over-interpret an image, just like as children we enjoyed watching clouds and interpreting the random shapes. This network was trained mostly on images of animals, so naturally it tends to interpret shapes as animals.

    Less intriguing: to consider that similar networks (especially once giving "recommendations" to unquestioning end users) might ascribe e.g. criminal propensity or lack of creditworthiness to the odd proverbial "innocent bystander" by over-amplifying distinctions they "think" to have learned.

    The "Bad Blue sky" tank detector https://neil.fraser.name/writi... "might be apocryphal" (just like the Obstinate Lighthouse http://www.snopes.com/military... ;-)) but instructive nonetheless.

  13. Some of those look like... by Anonymous Coward · · Score: 1

    the paintings that one dude did of cats as he got more and more schizophrenic

    1. Re:Some of those look like... by weilawei · · Score: 2

      Louis Wain:

      There has been some speculation that Wain’s schizophrenia was caused by toxoplasma gondii—a parasite found in cat’s excreta. Whatever began the illness, Wain was incarcerated in various asylums and mental hospitals for years at a time. The changes to his life were reflected in his art. His paintings of cats took on a radiance and vitality never before seen: the fur sharp and colorful, the eyes brilliant, and a wired sense of unease of disaster about to unfold.

      But these paintings look normal compared to the psychedelic fractals and spirals that followed. Though these are beautiful images, startling, stunning, shocking—they suggest a mind that has broken reality down to its atomic level.

      Though it is believed that Louis Wain’s paintings followed a direct line towards schizophrenia, it is actually not known in which order Wain painted his pictures. Like his finances, Wain’s mental state was erratic throughout his life, which may explain the changes back and forth between cute and cuddly and abstract and psychedelic. No matter, the are beautiful, kaleidoscopic, disturbing and utterly mesmerizing.

  14. Have you not heard? by Anonymous Coward · · Score: 0

    Timothy Leary's Dead

    He'll take you up, he'll bring you down
    He'll plant your feet back firmly on the ground
    He flies so high, he swoops so low
    He knows exactly which way he's gonna go

  15. does this explain dreaming and the "mind's eye"? by Anonymous Coward · · Score: 0

    Is what we see in our head a result of playing back things we've seen before and thus now know how to recognize?
    It could certainly explain why sometimes we think we see things we're searching for when they really aren't there.

  16. Re:does this explain dreaming and the "mind's eye" by Tatarize · · Score: 3, Interesting

    To some extent yes, but it's likely way more complicated than that. But, yeah, without sensory input we start hallucinating. It's like asking your senses repeatedly "is that real" and the senses always say yes, rather than no. So you drift off into whatever because that's real and therefore there's this other things too.

    It's a bit like that old parlor game where you tell somebody that you're going to have them ask questions about a dream, send them in the other room, asking for dream volunteers, and then tell the people still in the room that the answer is yes if the last letter of the last word of the question ends A-M and no if the last letter of the last word of the question ends N-Z. -- They inevitably guess a dream involving all manner of perverted stuff as the crowd confirms and rejects bits at random. Inventing a dream out of his own head rather than somebody else's head.

    There's also every day hallucinations like seeing detail where it doesn't exist, movement where it doesn't exist, and hallucinating something to fill the big blind spot in our eyes.

    --

    It is no longer uncommon to be uncommon.
  17. Source code? by Anonymous Coward · · Score: 0

    I'd love to tinker with something like this... is anything like this open-sourced anywhere?

  18. Definite resemblance to Wain's cats by dpbsmith · · Score: 1

    I see an intriguing resemblance to Wain's cats--paintings made by Louis Wain, while going insane, perhaps from schizophrenia.

    --

    "How to Do Nothing," kids activities, back in print!

  19. Oh, sure... by hhas · · Score: 0

    ...feeding these neural nets random images is all fluffy and fun right now, but just wait until someone forgets to turn SafeSearch on; and then it's the rise of Skynet all over again...

  20. Better pictures? by sound+vision · · Score: 1

    Are there any higher resolution pictures available? I'm sitting on a crappy 1024x600 monitor now, and these pictures don't even max it out. Seriously, why are these pictures in such shitty resolution?

    1. Re:Better pictures? by Ed+Avis · · Score: 2

      Perhaps the input images they used were also low-res? If they had used higher resolution photos it would have taken much more computing time to run them through the neural network for hundreds of iterations. I guess the same neural networks could also enhance the resolution of the images by being fed a scaled-up version and outputting it with more (imagined) detail.

      --
      -- Ed Avis ed@membled.com
  21. How close? by cjellibebi · · Score: 1

    I'm curious. Do the visuals just look different or do these psychedelics affect you at a much deeper level (eg. affect the thoughts and not just the visual perceptions)? Have you tried taking a small dose just to see what a 'low-intensity trip' is like? Can you use these photos and the knowledge of the article as a stepping-stone to describe what you do see when you are tripping?

  22. Implications for the demoscene by cjellibebi · · Score: 2

    Does anyone know if these images can be created in real-time? If so, demo-coders will pounce on the algorithm and have an absolute field-day! Demos will never quite be the same again. Another idea could be an easter-egg for a video-game where if the player has just ended a very intense gaming-session, the visuals of the frontend (even if only the background) could have this algorithm applied to them just to see if the player notices anything out of the ordinary (after a particularly intense session, this will be harder to spot immediately).

    I know that training a neural network can take a very long time, but using it to recognise images can be done very quickly. If a standard CPU or GPU cannot do this in realtime, would the more dedicated demo-coders start creating their own FGASs / ASICs that are designed just for this task, and bringing their creations along to demoparties?

  23. Reverse- engineering psychedelics by cjellibebi · · Score: 1

    I've never taken any psychedelics myself (so I guess you could call me a psychedelic layperson), but have read several experiences from people who have. One of the things my brain tends to do during it's 'down-time' is to try and interpret these experiences (from the point of view of someone who's not had any first-hand psychedelic experiences) and using my knowledge of neural networks and other geeky things, to try and figure out what is really going on, and hopefully in the process, to figure out the nature of conciousness. I expect this is something I'm almost certainly not going to achieve by myself and it may take several generations until a purely intellectual link is found between the experiences of a deep trip and the realm of scientific and philosophic explanation. Basically, this is attempting to solve the problem by approaching it from the other end. People like Terence McKenna try their best to bring back what they experienced on their trips, but are limited by the lack of established concepts related to what they saw - hence they don't have the tools to properly communicate these things. Because of this, their interpretations tend to focus more on the spiritual side of things than the intellectual side. What people on this side of the 'psychedelic divide' are doing is to try and construct the prerequisite concepts required to properly interpret the ramblings of Terence McKenna

    After reading the comments to this Slashdot article and comments posted on the linked articles, some people say it's the closest to a trip they've ever experienced on a purely visual level. Because the article attempts to make sense of what is going on, this could be an important step in developing means of communicating the content of the psychedelic realm. We could also see implications at the other end and figure out exactly what the brain does when tripping - a gold-mine of information for understanding how the brain works.

    One thing I've often wondered: what is an antomic unit of a psychedelic experience? My current theory is that any surreal juxtaposition that can break the mind out of the boundaries imposed by the Sapir–Whorf hypothesis could end up displacing the mind in an unknown state, and possibly even create a feedback-loop trying to make sense of it. Perhaps when tripping, the mind is automatically bombarded by so many of these experiences that they may end up gaining insight into the Ultimate Secret of the Universe. Perhaps this is what people who are 'trying to find God' are trying to find. So we could say that God is hiding behind a certain yet-to-be-entertained juxtaposition.

    Can someone who's actually had a trip please confirm if I'm on to something, or if I'm just talking out my arse?

    1. Re:Reverse- engineering psychedelics by cjellibebi · · Score: 1

      I think this comment on another article is of relevance here.

      One possible way of establishing frames of reference (eg. trying to explain the taste of an orange to someone who's never tasted a citrus fruit) is to figure out how to manually stimulate neurons (this does not necessarily involve brain-implants - maybe this can be done purely by meditation or something) and finding out which ones to stimulate for oranges and generic citrus fruit. Then, we could develop vocabulary that can be used to generalise combinations of simulated neurons, and from there, build a platform to intellectually venture deep into the realm of the psychedelic.

      I mentioned in the parent-post that an atomic unit of a psychedelic experience might be a surreal juxtaposition. Maybe it's actually trying out something completely new for the first time (eg. a citrus fruit), or even something slightly new (eg. an Orange if you've already had another Citrus fruit), but this may just create a new memory rather than attempt to shift the train of thought outside of standard thought-patterns, so it will just be chalked up as a new experience rather than a psychedelic experience.

  24. What? by Anonymous Coward · · Score: 0

    But that's the way I see things all the time!

  25. Used in image upscaling by zAPPzAPP · · Score: 1

    I have seen this used for upscaling image resolution.
    The neural net is trained on a certain type of image (comics/manga in the example below). It then uses its knowledge about how such a picture should look, to fill in missing information and remove artifacts during the upscale process. Kind of like the nets in the story will try to see their animals/objects in clouds and static.

    The result can be really amazing if used on the right type of image. I got some perfect results increasing the image size 16x from a small (300x200) source.
    However feed it with a 'wrong' (for example a photo of a person) type of images and the result looks horrible just running through the filter.
    The results also vary a lot in general for each source image, which I guess must be the result of how good it fits the training set.

    Example trained on comics/manga:
    http://waifu2x.udp.jp/

  26. What if they trained it to see Christ by Anonymous Coward · · Score: 0

    What if they trained it to see Christ and then gave it pictures of toast or tortillas or clouds or...

    1. Re:What if they trained it to see Christ by cjellibebi · · Score: 1

      Then eBay will be full of charlatans preying on gullible religious people. If they enhance the Jesus-like properties of a burnt spot on a piece of toast, at least when they deliver the toast and the customer is not satisfied, they will still be able to point out similarities between the burnt spot and a more Jesus-like blob as shown in the photo.

  27. Wrong, moron by gladius17 · · Score: 1

    It makes pretty pictures, but as far as psychedelic experiences are concerned, there is absolutely no knowledge to be gained here.

    Speak for yourself, dumbass.