Author Topic: mini A.I investigations  (Read 1222 times)

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
mini A.I investigations
« on: November 26, 2016, 07:45:02 PM »
current topic : what causes humor

give an example of something that made you laugh try and explain why it was funny.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #1 on: November 26, 2016, 09:10:01 PM »
why do I find this funny :

how many tooths are not enough tooths ?

keghn

  • *
  • Starship Trooper
  • *******
  • Posts: 302
Re: mini A.I investigations
« Reply #2 on: November 26, 2016, 09:34:08 PM »
 In a AI machine applying AGI theory. It is based on internal reward system. Humor is the activation of negative reward and
positive reward at the same time. The positive reward is the discovery of something new and the anti reward is failure to
predict it.

 True neutral rewards are undetectable. But a equal in strength positive and negative reward are. This is a rough neutral
reward.

LOCKSUIT

  • *********
  • Terminator
  • Posts: 875
  • First it wiggles, then it is rewarded.
    • Enter Lair
Re: mini A.I investigations
« Reply #3 on: November 26, 2016, 10:29:58 PM »
keghn, everything you "see" means you are doing/talking actions (+ marked). Negative marked actions almost have no purpose, one purpose is to make nearby + actions not be selected (negative always gets higher rank) = searching sense keeps on searching.

Now not really seeing the design of a couch's stitching ex. I can't really see it nor drawn it means the input ex. internal thought senses is *Faint. Faint can't search memory that good. No + actions are selected. You no "see". Ex. remember a memory of santa on a chair holding a child, now see it, now you reallllly see it.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #4 on: November 27, 2016, 06:58:49 PM »
it appears to be unexpected but also something else.
rain is unexpected but it isn't funny

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #5 on: November 27, 2016, 07:10:38 PM »
is this funny ::
lisa simpson getting small pox
?

keghn

  • *
  • Starship Trooper
  • *******
  • Posts: 302
Re: mini A.I investigations
« Reply #6 on: November 27, 2016, 08:26:31 PM »
 Novelty.

 Well there are two main way that the future become ture. First from the given data, a person can make a prediction into
the future. The second, is you wait and see where all the pieces fall into place and see the results.

 If i hear the same joke too many times i know what to expect. If i could use a 3d simulator and put my ghost into
some hearing the joke for the first time then i can relate to the novelty again.

 When i am putting something together and come it out different. I could laugh. Or if i am in a hurry or my boss is watch
 or i am competing against other building the same thing. Then there is no humor but a tempor.
 But in a not so urgent environment and with friend it is humor.

 I i am drive to somewhere and i end up at a different place that could be funny.
 if a lady is with me and i end up in the wrong place then it not funny. Or i am working on a movie and show
up at the wrong shooting location and late then it is not funny, but a bad temper. If someone else could use a 3d simulator
and put their ghost in my shoes then it could be funny for them if they are in a relaxed environment it would be funny
to them and also novel. if this happened too many time that person will not take notice. But if it is a fellow worker then he
will get mad, And if it is my boss then it will be worse.

 I may take notice when i first wee it rains for the first time for a minute. I make take notice the next time it rained and the duration is twice as long, two minutes. I may not take notice when it rains a minute and a half. But i will notice if rains for three minutes, because it is out of the predicted range. And up date my internal model.
 Being very young and unable to read a forecast it is novel and not funny but interesting.
 Once i know what rain is, i may find it funny when it rains when the sun is out.






 

keghn

  • *
  • Starship Trooper
  • *******
  • Posts: 302
Re: mini A.I investigations
« Reply #7 on: November 27, 2016, 08:29:58 PM »
 She only can get it once.
 Is it your kid?
 She can get sick again, boring.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #8 on: December 17, 2016, 06:34:14 PM »
is explore a goal ?
is seeing new things a goal or something else ?

kei10

  • It's a honor to meet everyone!
  • *
  • Starship Trooper
  • *******
  • Posts: 441
  • Just kidding.
Re: mini A.I investigations
« Reply #9 on: December 17, 2016, 08:44:47 PM »
You asked something that had been answered already.
Greetings, signature.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #10 on: December 17, 2016, 09:00:29 PM »
yeah but its different this time.

if you travel a long distance exploring from your house for say 5 hours
you save about the same amount of check points as learning a dance that takes 4 minutes
so what triggers the save of a check point ?

I mean you don't memorize every traffic light light why is that ?

Art

  • At the end of the game, the King and Pawn go into the same box.
  • *
  • Hal 4000
  • ******************
  • Posts: 4202
Re: mini A.I investigations
« Reply #11 on: December 19, 2016, 12:16:16 PM »
(You + Prank) - Me = Humor
In the world of AI, it's the thought that counts!

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #12 on: December 24, 2016, 08:26:43 AM »
how do you think data is stored in the brain ?

arrays ? dictionary type ? lists ? stacks ?

kei10

  • It's a honor to meet everyone!
  • *
  • Starship Trooper
  • *******
  • Posts: 441
  • Just kidding.
Re: mini A.I investigations
« Reply #13 on: December 24, 2016, 10:00:52 AM »
how do you think data is stored in the brain ?

arrays ? dictionary type ? lists ? stacks ?

https://www.quora.com/What-data-structures-does-the-human-brain-use

http://cogsci.stackexchange.com/questions/8646/what-is-the-data-structure-used-by-the-brain-to-store-data

https://news.ycombinator.com/item?id=3087659

One of them caught my attention:

Quote
The Neurological Engineering Framework does not explicitly state a mechanism for memory. There is no "hard-drive" in the brain for easy retrieval and access. Rather, memory is captured in the connection weights between neural populations and the dynamics of the network.

In the Hierarchical Reinforcement Learning example, linked to in the previous question, the "memory" of the map for the navigation task is saved by modifying the connections weights of the neurons representing the environment.

In the serial list memorisation task, the working memory for saving the semantic pointer list items is preserved in an integrator, which is essentially a neuron population that feeds back on itself.

These are examples of working memory, in other words, the memory that allows you to drive a car without really remembering how exactly you drove it. Long term memory modeling requires quite a few more mechanisms (memory reconsolidation) and structures (hippocampus, amygdala) that haven't been captured in any system built with the NEF yet.
Greetings, signature.

yotamarker

  • *******
  • Starship Trooper
  • Posts: 400
Re: mini A.I investigations
« Reply #14 on: December 24, 2016, 11:48:42 AM »
that is the physical structure of the memory but not the type of memory
which could only be deduced algorithmically.

 

Welcome

Please login or register.



Login with username, password and session length

Users Online

20 Guests, 1 User
Users active in past 15 minutes:
kei10
[Trusty Member]

Most Online Today: 44. Most Online Ever: 208 (August 27, 2008, 08:24:30 AM)

Articles