[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y ] [Search | Free Show | Home]

Okay Sci, what if we take a happy little image recognition neural

This is a blue board which means that it's for everybody (Safe For Work content only). If you see any adult content, please report it.

Thread replies: 13
Thread images: 1

File: Time.jpg (426KB, 3496x1680px) Image search: [Google]
Time.jpg
426KB, 3496x1680px
Okay Sci, what if we take a happy little image recognition neural net, and plug it into the output of a scanning self referential bitmap formula, as well as one more neural net that could compare image output to current real phonographs of transpiring events, so that the engine will with a specific reference for time, be able to search images it believes are true to reality, from the bitmaps potential configurations, enabling the user to see in time to the best ability of the neural nets.
essentially its a high tech chronovisor idea, what do you think?
>>
no takers? man, what a bunch of tards, as usual i'm a 168 genius floating around in a sea of non actors. the human race is fucked.
>>
>>8714569
This is the stupidest thing I've ever heard

What would the input even look like

It would probably just end up predicting based on past events anyway, and give loads of nonsequiturs
>>
>>8714836
not if you train the image recognition ai to search throught the formula for images of things it can identify as having form, this thing could be done and tuned, if you think not, show the work, genius.
>>
>>8714836
the ai is trained on a sample set of real images untill it has a good nose for organized forms, and then it is fed, in mukltiple threads every possible conifiguration of pixels in a limited bitmap, the primary imaging ai then indexes the positions of every image of value in the string, then anoter ai sorts through those for the best candidates for real things, in reference to a search query, the user then searches for relevant images from the hits, additional sorting tiers could be layered in for more accuracy and etc.
>>
>>8715273
if nothing else this thing could generate original images from the aether and that alone is interesting
>>
>>8714836
maybe it would produce untold abominations, that would be pretty tight
>>
>>8714569
if you could make the searching net layer favor those events which pair huristicly to a sequence of predicted frames, maybe one could organize enough data between neural net layers to actually form a video
>>
>>8714569
it would definately need more than two neurl; nets to work unless they were pretty powerful, and the task could be translated into terms in\t could follow, sorting that much data, essentially every possible configuration of an unspecified resolution of pixels would be hella difficult to do in any simple way
>>
>>8714569
darpa level shit
>>
>>8714569
I'm gonna try this, and see what happens
>>
>>8715370
post results, it's not science if you don't record results
>>
>>8714569
You forgot to mention some realtion to space itself. cause it simply can't work if it displays random times at random places, but a correlaton with something like a Geo coordinates might give you some low granular, few seconds or minutes future prediction. But nothing too fancy
Thread posts: 13
Thread images: 1


[Boards: 3 / a / aco / adv / an / asp / b / bant / biz / c / can / cgl / ck / cm / co / cock / d / diy / e / fa / fap / fit / fitlit / g / gd / gif / h / hc / his / hm / hr / i / ic / int / jp / k / lgbt / lit / m / mlp / mlpol / mo / mtv / mu / n / news / o / out / outsoc / p / po / pol / qa / qst / r / r9k / s / s4s / sci / soc / sp / spa / t / tg / toy / trash / trv / tv / u / v / vg / vint / vip / vp / vr / w / wg / wsg / wsr / x / y] [Search | Top | Home]

I'm aware that Imgur.com will stop allowing adult images since 15th of May. I'm taking actions to backup as much data as possible.
Read more on this topic here - https://archived.moe/talk/thread/1694/


If you need a post removed click on it's [Report] button and follow the instruction.
DMCA Content Takedown via dmca.com
All images are hosted on imgur.com.
If you like this website please support us by donating with Bitcoins at 16mKtbZiwW52BLkibtCr8jUg2KVUMTxVQ5
All trademarks and copyrights on this page are owned by their respective parties.
Images uploaded are the responsibility of the Poster. Comments are owned by the Poster.
This is a 4chan archive - all of the content originated from that site.
This means that RandomArchive shows their content, archived.
If you need information for a Poster - contact them.