KorrBot

  • 59 Replies
  • 1432 Views
*

korrelan

  • Trusty Member
  • *********
  • Terminator
  • *
  • 905
  • Look into my eyes! WOAH!
    • Google +
Re: KorrBot
« Reply #45 on: April 17, 2018, 02:40:37 pm »
@Art

I guess you just seem like a silver car… kind of person lol.  ;D

@Lock

Quote
Soon it'll be time to give it a test here!

Nice resource. 

Using NAME is a human, humans are mammals, etc must be common testing solution, strange how close my test sentences where… and I’d not see this site.

 :)
It thunk... therefore it is!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #46 on: April 17, 2018, 02:45:25 pm »
Omg that site is very close to my stuff. WOW. CIA Harry detective baby!!

LOL "Harry's native language is "Commando""

That site is good resourse, it has CIA test, Harry, mind overview.
http://mindmap.iwarp.com/

lol one of his things says "Transform sentence."
Emergent

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #47 on: April 17, 2018, 05:16:27 pm »
This is korrelan's expression when he saw that website:
Emergent

*

8pla.net

  • Trusty Member
  • *********
  • Terminator
  • *
  • 966
    • 8pla.net
Re: KorrBot
« Reply #48 on: April 18, 2018, 10:45:23 pm »
Hey Korrelan,

I am enjoying your videos.

Thank you.
My Very Enormous Monster Just Stopped Using Nine

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • ********************
  • Cleo
  • *
  • 4805
Re: KorrBot
« Reply #49 on: April 19, 2018, 04:10:56 am »
Agreed! Keep it up, you're not that far away from entering those, "My Chatbot is smarter than your Chatbot" contests!!  ;)

You can make it happen... O0
In the world of AI, it's the thought that counts!

*

8pla.net

  • Trusty Member
  • *********
  • Terminator
  • *
  • 966
    • 8pla.net
Re: KorrBot
« Reply #50 on: April 20, 2018, 12:03:37 am »
INTERFACE UPDATE:

http://aihax.com/MLP/

While it's not connected to the Deep Neural Network yet.
It does write an array of the training inputs and outputs
from the brand new training interface module.

My Very Enormous Monster Just Stopped Using Nine

*

Art

  • At the end of the game, the King and Pawn go into the same box.
  • Global Moderator
  • ********************
  • Cleo
  • *
  • 4805
Re: KorrBot
« Reply #51 on: April 20, 2018, 03:26:00 am »
Your interface does not seem to be working properly. If one touches the colored area with their cursor and scrolls the mouse wheel, the colored area shifts upward as shown in the screen cap.

Probably just a slight fix but I thought you should be made aware of the snafu.
In the world of AI, it's the thought that counts!

*

8pla.net

  • Trusty Member
  • *********
  • Terminator
  • *
  • 966
    • 8pla.net
Re: KorrBot
« Reply #52 on: April 21, 2018, 04:48:54 am »
Thanks Art!

I can't explain that. It's like it has a mind of its own.
Maybe the Deep Neural Network was hungry
for those training inputs, and tried to escape.  ;)

Apologies Korrelan for my deep neural network
running amuck on your thread with your readers. 

It's back in the cage now ( I think. )
I tightened the chains on the interface.




My Very Enormous Monster Just Stopped Using Nine

*

korrelan

  • Trusty Member
  • *********
  • Terminator
  • *
  • 905
  • Look into my eyes! WOAH!
    • Google +
Re: KorrBot
« Reply #53 on: April 21, 2018, 11:36:47 am »
Quote
Apologies Korrelan for my deep neural network running amuck on your thread with your readers.

Not a problem… It’s always good to see other projects, no matter how unruly they are lol.

As I improve the Korrbot and it’s functions become more complex, I’m finding it difficult to track what it’s learned.

So I’ve wrote a little app to display it’s knowledge trees.  I can now easily visualise the data and add to it visually/ dynamically.



This is the first incarnation of the code; It will be improved along with Korrbot. The link colours will represent the predicate and the nodes the objects and subjects. It runs in 3D as well and has been designed for ease of use on my large touch screens.

If anyone has any ideas to improve the visualisation or vids of similar systems I can nick ideas from... speak up.

 :)
« Last Edit: April 21, 2018, 12:45:53 pm by korrelan »
It thunk... therefore it is!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #54 on: April 21, 2018, 01:10:38 pm »
I really like where this is going.

Can you make it form i.e. generate discoveries by first searching through the branches ex.
Hammers canBreak crystals, glass isA crystal, therefore hammers canBreak glass!
Hammers canBreak glass, windows areMadeOf glass, therefore hammers CanBreak windows!
Hammers canBreak windows, windows cost money, therefore hammers canBreak money!)

Is it possible to combine the 3D tree/net you have there with Parse Trees to make it stronger?

And what about the attachment to this post (see attachment).

Keep it simple so you can make new milestones. Do something new here.
Emergent

*

korrelan

  • Trusty Member
  • *********
  • Terminator
  • *
  • 905
  • Look into my eyes! WOAH!
    • Google +
Re: KorrBot
« Reply #55 on: April 21, 2018, 04:29:34 pm »


Haha... highlighted a problem with double 's'... glass, I'm sure many peeps have had that problem before... lol

Hmmm... time to explain the transference/ conversion of energy types and material properties to the bot... lol

I'm glad this chatbot is just a bit of fun... and my AGI will solve all these problems.

 :)
« Last Edit: April 21, 2018, 05:08:10 pm by korrelan »
It thunk... therefore it is!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #56 on: April 21, 2018, 06:27:40 pm »
Hmm, it made a big connection loop I see there. So basically you said "Can hammers break windows?", then it says hmm maybe it's true, then it search-verifies the Transfer Learned (Acquisition) generation from you and calculates that it is true and says yes.
Emergent

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #57 on: April 22, 2018, 10:54:28 pm »
Also, I realized something. It could learn "Iron-man loves crystals." (instead of "Windows areMadeOf glass."), and this presents a problem to which I have a solution. See, your algorithm found a in-direct connection loop that A=B B=C etc etc but....it can do that with anYthiNg, and easily become ultra pointless. Solution? You need confidences (weights!) of how much ex. B=C. Because if glass literally IS or "=" crystals, then hammers can break crystals and likely glass too, whereas if ironman loves crystals then it won't conclude hammers can break his iron-solid body if it really isn't connected or "=" crystals. Confidences (connection weights) also for how many facts support something (3 things weight-in one 1 node). There's also positive/neutral/negative integer ranks. Also another type of confidence for the probability of how true a fact is, ex. "Hammers canBreak iron man." has a probability of being 4% true.

What's pretty amazing that I myself discovered (I discovered a similarity between 2 things) is, Ray Kurzweil says intelligence saturates the universe with intelligent processes, and yet here we have (as I alssoo discovered by myself) Saturation of beliefs happening, where it uses its facts it has in its network and saturation discovery of new facts occurs and improves.
Emergent

*

korrelan

  • Trusty Member
  • *********
  • Terminator
  • *
  • 905
  • Look into my eyes! WOAH!
    • Google +
Re: KorrBot
« Reply #58 on: April 22, 2018, 11:39:34 pm »
Ed: Yes the chain event with using Iron man would have caused a problem... and yes I solved the problem by storing numerical values against the objects. So the tensile strength, brittleness and thermal properties for example can be applied to a set of functions.

I've just started writing the library of functions; so the bot can apply numerical judgements, formulas, rules, etc.

Still a bit rough around the edges but I'm very limited on time just lately.



 :)
« Last Edit: April 23, 2018, 09:51:22 am by korrelan »
It thunk... therefore it is!

*

LOCKSUIT

  • Emerged from nothing
  • Trusty Member
  • ***********
  • Eve
  • *
  • 1456
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: KorrBot
« Reply #59 on: April 23, 2018, 11:53:50 pm »
Did you know vision can be sentences for discovery too? Looking at a hammer is the word hammer. Seeing a video sequence of a hammer smashing crystals is the sentence "Hammer smashing crystals." I can actually say by speech the top node sentence in ONE word - slap, faster than having to see it visually. This is because every sequence is just so you recognize 1 high-level node, and unless you're in the real world rogue, you can use symbols to say sentences by ONE word. Seeing a dinning table of soldiers guarding a pod from aliens are sentences that build up to select/create a higher-level node in a hierarchy net. But these are single images that are instantly recognized sentences (no sequence waiting time). I can speak: Guarding, which is like saying Slap, not needing a sequence to recognize a sentence. Lastly vision

Hmm, if HUGE marshmallows (their tiny core) areMadeOf crystals, glass isMadeOf crystals, windows AreMadeOf glass, and windows cost money, then, if you ask "Can hugeMarshmallows break windows?", well, it can't begin the loop/connection around BY "predicate weight" because in the case it had learned that hammers canBreak crystals - the link predicate "canBreak" is not as strong as MadeOf (Madeof is stronger yet no proof hammers can break anything). And here with the hugeMarshmallows we have a predicate link "MadeOf" to crystals which is strong but doesn't say anything about being able to break anything. Hence this example loop would loop around and wrongly conclude hugeMarshmallows canBreak windows if asked so. SO, weight forwards a connection? No... So then is it predicate NAME? I guess so.

Therefore, if hammers have not been known to canBreak anything, it can see that hammers are hard and hard things canBreak things but if nothing has been known to break, then no worky...

It needs to know the definition of what break means i.e. hard objects can break/hurt brittle and living objects.

So............You ask "Hammers canBreak windows?". Then it searches to verify this and it sees that hammers canBreak crystals. Then it looks from there, and finds glass isMadeOf crystals, great, but before it calls it a possible step forward for looping around to the question nodes, it first looks at the properties of hammer>crystals and crystals>glass for similarities. Mini discoveries supporting bigger discoveries. It can also look at the properties of crystals and windows/glass to look for commonalities.

A predicate can have a direction/arrow of flow. If one is the opposite way, it'd stop the loop from going around.

So far we got flow, mini discoveries, weights, and predicate names.

Socrates isA man, man isA mortal, therefore Socrates isA mortal. And the hammer example. Both you ask if hammers/Soctrates canBreak/isA windows/mortal. Then BOTH nodes (ex. hammer node and window node) look to see if there is any identical predicate names protruding out of themselves ex. oh, well "hammers canBreak crystals" or "windows canBreak rocks" backwards. Further, once it finds a identical predicate exists, well then if any connected literally "=" it i.e. isMadeOf, then essentially simply saying "Hammers canBreak crystals" is saying "Hammers canBreak windows".

Try making a belief self-ignite like "Hammers canBreak crystals" but when it fires make it get tweaked at the end word so it might become ex. "Hammers canBreak rocks/glasses/paper/etc". Then have it see if it can form discoveries towards a goal it desires. Also if both light up (Hammers canBreak crystals & Hammers canBreak windows), then, it can compare them to look for commonalities or look for commonalities by looking for a connection between them like we've been doing here.
Emergent