[agi] Android Legs

2019-05-08 Thread rouncer81
Little robot walking along,  it works it out itself, I just tell it where to head. https://www.youtube.com/watch?v=6HnMPvNpEP0 -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T33c2866816e1d05d-Ma2315f891d88db4ffc

Re: [agi] My AGI 2019 paper draft

2019-05-11 Thread rouncer81
Looking 3 moves ahead in chess, counts for a lot more than looking 3 moves ahead if your walking down the street. =D -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-M07a1c8ac9ad7b0e321740276 Deli

Re: [agi] My AGI 2019 paper draft

2019-05-11 Thread rouncer81
I think its a good thing,   need diversity, otherwise things get a little drab and over discussed. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-M86eb314888de44bf7c1cc3e7 Delivery options: http

[agi] Re: Android Legs

2019-05-11 Thread rouncer81
I need a better physics engine DAMMIT!!! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T33c2866816e1d05d-M5e51508c123bb25c466cdbbf Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: Android Legs

2019-05-12 Thread rouncer81
Thanks Keghen! =D   u 2! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T33c2866816e1d05d-Mfb82037f5933fb23a079acf8 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] My AGI 2019 paper draft

2019-05-12 Thread rouncer81
Nice slides... thanks for the help ill tip you from where I sit. Yes the search, is a nice alternative for the ai problem,  but its too expensive,   and for some reason no-one has a quantum computer yet.   If you did have NP power tho,   theres 3 more problems as I see it. a) You must have a mod

[agi] Re: Android Legs

2019-05-14 Thread rouncer81
I think I should be able to do it now.  But the program has an extreme bug in it!  I dont know what happened but its behaving illogically, and I dont know the cause... Once I get it done,   I think this machine will run and walk with a different gait!      Ill give it 2 more hours rest,  then w

Re: [agi] My AGI 2019 paper draft

2019-05-16 Thread rouncer81
Groundbreaking stuff!! :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323-M7443989d2da5c23fac19165e Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] How do I leave the group?

2019-05-17 Thread rouncer81
hahhahahahha    u must know fuckall about ai. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6cd9fbea2c00aa0-M488d0a88b77335380db8a4a3 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] How do I leave the group?

2019-05-17 Thread rouncer81
TRAITOR!! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6cd9fbea2c00aa0-M2c5e9ee7879474166506f07c Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: The 3 mental spaces

2019-05-17 Thread rouncer81
Ill join your group.  but I have my own projects,  we can help each other.    here is my presentation portfolio (only 1 thing) just to let you know i am crazy about ai...    https://scontent.fper6-1.fna.fbcdn.net/v/t1.0-9/41459348_761716900843036_3685750769455202304_n.jpg?_nc_cat=109&_nc_ht=scont

Re: [agi] How do I leave the group?

2019-05-19 Thread rouncer81
A.I. is a pretty zany thing to get running,  maybe it helps to be a crackpot,  means ull be successful. :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6cd9fbea2c00aa0-Mf96cb5770ba30c1d4ca7c528 Delivery optio

[agi] Re: The Pattern Machine - Part 1: What is Deep Learning?

2019-05-19 Thread rouncer81
I have this new alternative to genetic algorythms.    Chaining monkeys to typewriters!  Given enough - I can always get the right answer. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T32be78ee6298e617-M1aedd2cb

[agi] Re: The Pattern Machine - Part 1: What is Deep Learning?

2019-05-19 Thread rouncer81
yes.  its how amazing "deep learning" actually is.  :P -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T32be78ee6298e617-M6028476fedb0ba965be3a7ff Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Re: The Pattern Machine - Part 1: What is Deep Learning?

2019-05-19 Thread rouncer81
and new!  -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T32be78ee6298e617-Ma4beda450d091beffa3e3d3a Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: The Pattern Machine - Part 1: What is Deep Learning?

2019-05-19 Thread rouncer81
no. i  am against such amoral practices.   I just stick with information technology,  take me all the way already. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T32be78ee6298e617-Md36de14576f5fa8a2765b14a Delive

Re: [agi] How do I leave the group?

2019-05-19 Thread rouncer81
Its hard to tell if someone's theory is good or not.   You just have to know, or you wouldn't have a clue.   But I spose you opting to be skeptical, is a type of ignorant reaction indeed. -- Artificial General Intelligence List: AGI Permalink: https://agi.

Re: [agi] Do Neural Networks Need To Think Like Humans?

2019-05-19 Thread rouncer81
I think neural nets have to think LESS like humans.   just get the job done,  nature is a time wasting inefficiency, you dont need it AT ALL. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4aa81fd9912dbd39-Meaa1

[agi] Re: Android Legs

2019-05-19 Thread rouncer81
Not walking yet,  but ive upgraded my system for meshes of thickness plus tendons instead of rotations and hopefully the system will work better all round with less code. https://www.youtube.com/watch?v=9yIhHlI_MiE&feature=youtu.be -- Artificial General Int

Re: [agi] Do Neural Networks Need To Think Like Humans?

2019-05-19 Thread rouncer81
the brain has to deal with LOTS of hidden variables. Thats why it MUST be approximate - because a computer trying to simulate everything in detail is ALSO impossible!  So the real ai, artificial even, still needs to be approximate, but also true. If you were to simulate a car running,  you have

[agi] Re: Android Legs

2019-05-21 Thread rouncer81
The tendon system is nearly working now,  but its still bugged, but u can see it shrinking and expanding on the pink areas, and its due to these changing length, that it should work along.    this way is better because the system is less commands its a simpler idea. https://www.youtube.com/watch

[agi] Re: Android Legs

2019-05-22 Thread rouncer81
Tendon based robbers are indeed soft-body, it looks like a jelly fish. Ok, a bit more work.   all the dims are pulsating when I toggle all the tendons, but for some reason when the search is on, one of the knees goes into remission. That's just a side problem,   the main problem here is when the

[agi] Re: AGI Has Been Delayed

2019-05-23 Thread rouncer81
haha My theory is going fine.    goes to show WE ARE NOT EQUAL. we are sorrounded by goofballs. hhehehe -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5bedc18215c1530f-M97425f1cf1ed15d86d05a39d Delivery options:

Re: [agi] How do I leave the group?

2019-05-23 Thread rouncer81
ah get a taste of some nasty, dont be a wuss. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf6cd9fbea2c00aa0-M70b3d9a6956b2b6c0de7755c Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] AGI Has Been Delayed

2019-05-23 Thread rouncer81
great talk.  yeh now we know none of us know how to do it.  :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T5bedc18215c1530f-M64457eec47711900f991547c Delivery options: https://agi.topicbox.com/groups/agi/subsc

Re: [agi] AGI Has Been Delayed

2019-05-23 Thread rouncer81
Sorry for being a random and rude,  ill shut it up But I just want to say the answer to AGI is not difficult, and markov chains, genetic algorythms and computer vision put together will work,  ppl just have to wake up and realize weve already got what we need.

[agi] Re: searching for intelligence in NPC world

2019-05-26 Thread rouncer81
Sorry if im one of the random idiots you were talking about, but I have something to say. Im with you on the get the dumb stuff right first.   And getting tiggly puff waving his arms like a monkey is a great beginning, and maybe theorizing beyond this without a working implementation of at least

[agi] Re: synthetic personalities

2019-05-27 Thread rouncer81
This is "behavioral cloning" in open ai,  where the computer records your gameplay up against a set of possible causes, then can play you back.   It is possible to do,   but as for consciousness transfer,  it is but a soulless copy. -- Artificial General In

Re: [agi] Re: synthetic personalities

2019-05-27 Thread rouncer81
Doing your work with an api, in such a new field as a.i. is going to handicap you from doing anything new. Do your programming from scratch,  you can do it any programming language,    just the basic outline is all you need for an implementation,  but u do need programming experience,  more year

[agi] Re: Here is the sole reason why I don't progress faster

2019-05-27 Thread rouncer81
I have a possibly working theory too, Stefan,  Its a basic menial labour slave,  It revolves around a value state system, its like a flow chart that tells the robot where to go next, getting visualization id's off my computer vision system, scoring a motor search, which feels its way around 3 sp

Re: [agi] Here is the sole reason why I don't progress faster

2019-05-27 Thread rouncer81
50's perceptrons were super parallel mega beats.  love. And yes, I saw Ben Goerztels post,  I am going to be quiet now.  So he can see my writing?   I better be careful not to make a complete idiot of myself! :) -- Artificial General Intelligence List: AGI

[agi] Re: Scoreboards

2019-05-30 Thread rouncer81
if you cant beat the computer what the hell are u even doing there with ppls lives at stake... oh wait... we are in india. XD -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T4cd58d748dde7471-M4272ec695a8d54fe9ea4

[agi] Re: A mathematics of concpetual relations?

2019-05-30 Thread rouncer81
factors are important,  but symbology has a strength where its known to be true without detail. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-M0d4b1f523144931424b4e5d7 Delivery options: https:/

Re: [agi] Re: A mathematics of concpetual relations?

2019-05-31 Thread rouncer81
I mean you can make a symbolic system without factors,  but I guess you could have factors but it would be in the form of a weighting of a symbol, like "strength=6"  but without the 6, its purely only boolean algebra,  not algebra.  And it works without the 6 too,  is all I mean. ---

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-01 Thread rouncer81
I dont want to stop this amazing imagination of yours.   But I must warn you ockhams razor is there to dismiss ideas on the outset,   and maybe simplistic weighting is all there is to it.   You dont always need a factor, when the symbol itself already deals out the full picture.

Re: [agi] Re: The 75% AGI

2019-06-01 Thread rouncer81
Ive got one for you. You can actually make the computer spit out strings of text, and it can even reply to what you say,   but that involves not looking at the content of the strings. Word ai, would have to actually produce something from the content itself,  even if it was just more patterns to

Re: [agi] Re: Here is the sole reason why I don't progress faster

2019-06-01 Thread rouncer81
yes that makes mature sense.   Im pretty much isolating myself, but I dont mind. Ill help as much as I can from here,   if I know something I might be able to help you. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups

Re: [agi] I want bigger financing now

2019-06-04 Thread rouncer81
AGI has a 0 digit price tag I think,  you just have to know how it works.  -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc0eeba85ef9f57fd-M68777d0185dc896fa5620226 Delivery options: https://agi.topicbox.com/grou

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-04 Thread rouncer81
Ok, sorry about that misunderstanding. You need to form the model of the of the working area of the a.i. ,  its true for us all,  but how you do it, is what makes what your doing original. -- Artificial General Intelligence List: AGI Permalink: https://ag

Re: [agi] hmu

2019-06-05 Thread rouncer81
that was so funny keg when you said that  :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc47aa10d672cc421-M726afd6f0e0c50a544ce26f8 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] I want bigger financing now

2019-06-05 Thread rouncer81
love what u said.   motivation is the true riches... if only i could work that hard! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc0eeba85ef9f57fd-Mcbd5ad67cab181f7333084c9 Delivery options: https://agi.topicb

Re: [agi] I want bigger financing now

2019-06-05 Thread rouncer81
it runs on a shoe string. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tc0eeba85ef9f57fd-M235955dd2f9c97ba1c6cbfe8 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Re: Here is the sole reason why I don't progress faster

2019-06-05 Thread rouncer81
you know whats holding you back the most?  it are not money, it are not co-workers. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tbb6d8acb094a551f-Mda97872634ab980460d58b2e Delivery options: https://agi.topicbo

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-05 Thread rouncer81
Yes keghn,  you go to maximize the function, is the current going style. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-M1b5e07b1ccb6f78b3dd931fb Delivery options: https://agi.topicbox.com/groups

Re: [agi] AI Game Plan

2019-06-05 Thread rouncer81
Stefan Reich has a point where he says the language doesnt matter...  but taking everyones opinions into account you never know they might make a difference, i havent thought about it enough. -- Artificial General Intelligence List: AGI Permalink: https://

Re: [agi] AI Game Plan

2019-06-05 Thread rouncer81
Thats ok mate,  gotta love camels!!! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8e8cca32050f13ab-M89b27c1f045bba91632a5ac0 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-05 Thread rouncer81
ha, watch out, theories can catch on whether you like it or not. :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-Md569c6d0817b7e97204f890a Delivery options: https://agi.topicbox.com/groups/agi/

Re: [agi] The Turing test is a joke

2019-06-09 Thread rouncer81
good points. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8338053773565e1e-Mb3724c5a34c0ea16bcd7a08c Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-09 Thread rouncer81
Thats really interesting Mr. Richfield, id love to hear more about it and what it could be clues for.   Stuff working in the field (Like open ai) is still just based apon dumb mutation, they have this novelty search that would entail the robot doing everything just because its new.  If that was

Re: [agi] Pitrat's blog: “Singularity” is improperly used in AI

2019-06-09 Thread rouncer81
Lovely read.  Im with Mahoney on this one, Quantum computers CANT exist, and the agi if they make it, is not going to defunct the true animal brain. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T614fe8e29cc543f

Re: [agi] Pitrat's blog: “Singularity” is improperly used in AI

2019-06-09 Thread rouncer81
In chess, ppl can still keep up with the perfect game,  because the better the computer plays, in a way it makes it more obvious what its going to do. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T614fe8e29cc54

[agi] test driving your system on captchas

2019-06-09 Thread rouncer81
It seems that if you have an ai system running, you can attempt to solve captchas with it, you have audio, text, vision , but i dont know if there is some generic solution...  the generic solution is some kind of new ai system. The a.i. we make is an artificial brain, so it makes sense that u can

Re: [agi] The Turing test is a joke

2019-06-10 Thread rouncer81
Hey Reich - if you can do that it might be important.   get back to us if you manage to solve it plz. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8338053773565e1e-Mc87bf1615eb974aa4e0ab537 Delivery options: h

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-10 Thread rouncer81
Doing things over time isnt mandatory,  x and y on your graph could be any metric under the sun, yes. Have you looked at expert systems before?  They are a kind of symbolic logic machine,   where you break the problem up into constituent parts,   and presenting it with some information, and a g

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-11 Thread rouncer81
I can understand what your saying to a degree. Indeed if you trained a label "cat jumped out of the box" directly, its not the same as understanding cat, jump and box separately - which is alot more successful/invarient/reusable? The way you say this a "mathematics" problem, was alien to me, henc

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
This probably sounds stupid but.. With the generation idea, about getting the a.i. to develop images from an algebraic model.  It has a problem where the output is no longer symbolic (its pictures) I wonder it might be easier for the computer to describe it in words as if it was a picture...   s

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
Maybe the database doesnt have to be that big,  to do a lot.  I know that when one thinks of AGI he thinks of some great ginormous load of information,   but im just saying maybe small things could go really far as well. -- Artificial General Intelligence L

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
You can actually set up boolean algebra that solves all sorts of tasks, making it develop the structures itself would be more closer to real agi,  but it would still be quite effective setting it up for it, old school style. -- Artificial General Intelligen

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
Just imagine how boring it is to do the dishes.  programming it is probably more boring.  But we are grownups, we are boring, so it suits us to do it.  :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
Yeh Steve - maybe that helps it try novel situations better??? newsflash from me ->  i think that formalizing the system manually ends up a shallower system than what needs to be there for a developing system.    because its cheating it to do things,  is it where the term "deep learning" comes f

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-12 Thread rouncer81
If you give yourself infinite computation power an exponential brute force search of physics engine logic, contains all methods that exist in the environment, as long as it only involved still objects, which were simulated correctly,  according to some primary mover.    I was wonder if taking it

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-13 Thread rouncer81
This could be an alternative to mutation,  who wouldnt want to skip past having all that pesky trial time. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-Mbe272a2671c5d00ab994748b Delivery optio

Re: [agi] How to prepare an international AI offer

2019-06-16 Thread rouncer81
you dont need open cv if you can code it yourself. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T7dcc9b3c92fc827d-Meb309a3b689fc5b77a582041 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] How to prepare an international AI offer

2019-06-16 Thread rouncer81
Wow youve got agi already?  amazing! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T7dcc9b3c92fc827d-M9523c67d0c4f03238ab5ac93 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] My AGI 2019 paper draft

2019-06-17 Thread rouncer81
If ur solution is valid,  you dont need approval to get it going.    Theres no more understandable results than actually having the a.i. in action! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T3cad55ae5144b323

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-19 Thread rouncer81
you sound like you need something more than just random attenuation for learning. :) Your space-temporal rotation idea, sounds like geometric invarience for an advanced computer vision system. And my opinion is even if we had a more advanced "symbolic structure" or whatever thats building inst

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-20 Thread rouncer81
I think it would build up slowly over time,  it cant solve problems that are too far away from what it already knows,  it has to relate to what its got in it, for more relations to develop.   So in that way it would hit "temporary local optimas" and maybe even some form of cause and effect diagn

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-20 Thread rouncer81
The learning method is only as good as how much better it is than basic mutation type learning,  which I think actually it sounds like it wins in a logged fashion...  by a heap.  :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicb

Re: [agi] Re: A mathematics of concpetual relations?

2019-06-20 Thread rouncer81
Yeh Hebbian learning might be a means towards an unknown end,  and if its us, its going to be pretty amazing. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T395236743964cb4b-M72c00068ad5e9b9ec0a103fe Delivery op

Re: [agi] test

2019-06-24 Thread rouncer81
Theres nothing wrong with the state of the art,  and there never has been.    The technology works.   I think what we are lacking is a integration of the technologys into the working machine.  computer vision, symbolic ai, brute force search, all together used in unison should work. -

[agi] some fancy electronics

2019-06-27 Thread rouncer81
This oscillator has no transistor in it,     it is 2 caps and the rest is resistor balancing, and the bastard is f'n hard to start up! I was there for half an hour before i got it to buzz at around 10hz.  This is my video proof to myself just so I know the bloody thing even works at all! https

[agi] Re: some fancy electronics

2019-06-27 Thread rouncer81
https://www.youtube.com/watch?v=uOWTGmeCG68   heres a better video, i worked out if i increase delay each time i tap back on the battery it starts purring longer and longer. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/g

Re: [agi] Re: some fancy electronics

2019-06-27 Thread rouncer81
Haha you brightened my day.   Id get myself kicked off 100% of the electronics forums on the internet if I said the next thing I want to do is amplify with only resistors and capacitors  But since this is an AGI space I think ppl get away with more zanier ideas. Your right about the leaky c

Re: [agi] Re: some fancy electronics

2019-06-27 Thread rouncer81
just wait three hours,  and ill go jog off to the shop and get some led's,  and itll make it easier to see. Just to clear something up-> The "speaker" on it currently actually has an oscillator on it,   but mine is making it double oscillate,  its when it sounds like a cricket, is when its doub

Re: [agi] Re: some fancy electronics

2019-06-27 Thread rouncer81
so just be patient, ill be back with some more visible videos of it,  and i might point and poke at it so you can get a better idea. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-Mf5805cf6f0d28

Re: [agi] some fancy electronics

2019-06-30 Thread rouncer81
https://agi.topicbox.com/groups/agi    its dc. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-M3680e8ee40900b03bea5a43e Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] some fancy electronics

2019-06-30 Thread rouncer81
https://www.youtube.com/watch?v=1mZo0-KCRY8&feature=youtu.be   better view -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-Mffb7a576e1d4e46801da9947 Delivery options: https://agi.topicbox.com/grou

Re: [agi] some fancy electronics

2019-07-02 Thread rouncer81
mexican fire cracker https://agi.topicbox.com/groups/agi -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-M9ef898116a6b580c4ba5cd59 Delivery options: https://agi.topicbox.com/groups/agi/subscriptio

Re: [agi] some fancy electronics

2019-07-02 Thread rouncer81
https://www.youtube.com/watch?v=4ycdfkkZlZQ i mean -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-Ma26e6913a67c9aaec25f3d27 Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] some fancy electronics

2019-07-02 Thread rouncer81
https://www.youtube.com/watch?v=tr_81ztvVOs&feature=youtu.be  latest vid -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Td7a52e89327738b7-M917da1ddbd7053f2e80629b3 Delivery options: https://agi.topicbox.com/groups

[agi] Re: Reading comprehension, Lesson 1

2019-07-08 Thread rouncer81
amazing!!! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tfa2f5184f472f66a-Mae9c72bdd60d8d8586f3d231 Delivery options: https://agi.topicbox.com/groups/agi/subscription

[agi] Re: My thoughts on the 5 "houses of AI"

2019-07-08 Thread rouncer81
evolutionaries and connectionists and symbolism can be done as one,  in my mind. the more i learn, the more everything becomes the same.    it is such a boring useless existance being that way. -- Artificial General Intelligence List: AGI Permalink: https:/

Re: [agi] Hardware news

2019-07-08 Thread rouncer81
Why do gpus have 2048 cores when they should have 2048x2048. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T6dfb3d3150d6e94b-M11599bf4b3ea9c1c5a338820 Delivery options: https://agi.topicbox.com/groups/agi/subscri

Re: [agi] My thoughts on the 5 "houses of AI"

2019-07-08 Thread rouncer81
I think they need to be translated, like the rosetta stone. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tdf00fadf1198644a-M4fc4a0b665c5b1143a83e151 Delivery options: https://agi.topicbox.com/groups/agi/subscrip

Re: [agi] Hardware news

2019-07-10 Thread rouncer81
woah 5000,   thats not anywhere near 4 million.  And I think they can make 4 million cards but they keep them a secret. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T6dfb3d3150d6e94b-M520cddaf9caaab897d2c049d D

Re: [agi] Narrow AGI

2019-08-01 Thread rouncer81
Machines today only want what we make them want,  only we truly want things,    so if you want AGI you need to create something with a true purpose, not an artificial one. I think any more than narrow a.i. is blowing it out of superfluous proportions,  and we need something more important to do

Re: [agi] Controlled AI

2019-08-01 Thread rouncer81
Does the goverment have a strangehold on nuclear weapons - you have to try and learn it to find out if they lock u up in a 6 foot cube or not. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tdd7cd3380dc9f5a9-M8ae

[agi] Re: This might make it a really interesting Incomplete Information game to consider for AI research

2019-08-02 Thread rouncer81
Its a cool idea if you can make a game a computer cant play... its like a "captcha"  but if you make a mistake the computer actually can, and u have to come up with another idea. :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicb

Re: [agi] Controlled AI

2019-08-03 Thread rouncer81
Just imagine in the future giving the smash and grab technique self driving cars to do it.   seems like a good idea!!! -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tdd7cd3380dc9f5a9-Mad399665aef36275861da61a De

Re: [agi] My paper in AGI-19

2019-08-04 Thread rouncer81
Mohammud is a monkey. =CD -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf27122c71ce3b240-M515cda17e10583c9534d0d2e Delivery options: https://agi.topicbox.com/groups/agi/subscription

Re: [agi] How about a Markov chain to convert neural networks to Markov chains, then every step of action could be understood by a human or?

2019-08-05 Thread rouncer81
a neural network is basicly the same thing as markov chains.   if on the input of a feedforward perceptron you have the pattern of text,  and on the output end you have the next letter,  its doing exactly the same thing. -- Artificial General Intelligence L

Re: [agi] How about a Markov chain to convert neural networks to Markov chains, then every step of action could be understood by a human or?

2019-08-05 Thread rouncer81
woah, now were going crazy! I didnt mean that much,  all i meant was about a 5 letter input (a-z)-5 nuerons a lettah, mesh to about 5 neurons*1 meg internal patterns to give me a 1 letter output (a-z) 5 neurons a lettah,  get your redskin. Get a good near match on this sucker, probably start resp

[agi] can anyone here code a physics engine?

2019-08-05 Thread rouncer81
So... i'm at the point now ive got my artificial neural network system how I like it...   But I need a method to train it on. So, I thought - wot tha hay - lets get it emulating a physics engine. But then just the thought of 100 complex pendulums spinning around rattling into each other and bou

Re: [agi] My paper in AGI-19

2019-08-05 Thread rouncer81
90% of the indians live in the mud,  the rest of them had their house built by europeans -   and u ALL know its true. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tf27122c71ce3b240-M1523bbe022a820ca397e2414 Del

Re: [agi] You can help train desktop image segmentation

2019-08-27 Thread rouncer81
To my mind, this is the computer vision,  which is going to spark your symbolic relations. Segmentation, if you colour your segments of some video,  if you make everyone simpsons colours, it looks like "the real simpsons"   its potentially halarious. :) How is your ai going Stefan - are u stil

Re: [agi] You can help train desktop image segmentation

2019-08-29 Thread rouncer81
Good to here u still sound like your on top of things. I think theres no need for bad confidence,  theres going to be a simple solution for this singularity business. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/a

[agi] Re: I am releasing all of my AGI research soon

2019-08-29 Thread rouncer81
Dont forget, we need DNA samples as well to go with your amazing theories. :) -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Tb2c56499bd62ee8a-Ma0c503fa5aa8a8153756dd15 Delivery options: https://agi.topicbox.com/g

Re: [agi] You can help train desktop image segmentation

2019-08-29 Thread rouncer81
if you have a 3d camera, segmentation is even easier.     its not even really machine learning,  its just filters. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8f7f05f86e62415a-M4234fb42924e5b0138f99422 Delive

Re: [agi] You can help train desktop image segmentation

2019-08-29 Thread rouncer81
Matt Mahoney I have an argument against that,  computer vision ends before symbolic relations start. Your saying that your eye invents jokes with what it sees,  I say no,  the vision just classifies the visible aspect alone. The rest of the derivation of the eye is the rest of the brain. ---

Re: [agi] You can help train desktop image segmentation

2019-08-29 Thread rouncer81
Yep.  labels first,  actual understanding later on. -- Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/T8f7f05f86e62415a-Mcb4fa9e98e050133e8e97495 Delivery options: https://agi.topicbox.com/groups/agi/subscription

  1   2   3   4   5   6   7   >