Ai Dreams Forum

Artificial Intelligence => General AI Discussion => Topic started by: yotamarker on November 26, 2016, 07:57:02 pm

Title: mini A.I investigations
Post by: yotamarker on November 26, 2016, 07:57:02 pm
current topic : what causes humor

give an example of something that made you laugh try and explain why it was funny.
Title: Re: mini A.I investigations
Post by: yotamarker on November 26, 2016, 09:22:01 pm
why do I find this funny :

how many tooths are not enough tooths ?
Title: Re: mini A.I investigations
Post by: keghn on November 26, 2016, 09:46:08 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.
Title: Re: mini A.I investigations
Post by: LOCKSUIT on November 26, 2016, 10:41:58 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.
Title: Re: mini A.I investigations
Post by: yotamarker on November 27, 2016, 07:10:49 pm
it appears to be unexpected but also something else.
rain is unexpected but it isn't funny
Title: Re: mini A.I investigations
Post by: yotamarker on November 27, 2016, 07:22:38 pm
is this funny ::
lisa simpson getting small pox
?
Title: Re: mini A.I investigations
Post by: keghn on November 27, 2016, 08:38:31 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.






 
Title: Re: mini A.I investigations
Post by: keghn on November 27, 2016, 08:41:58 pm
 She only can get it once.
 Is it your kid?
 She can get sick again, boring.
Title: Re: mini A.I investigations
Post by: yotamarker on December 17, 2016, 06:46:14 pm
is explore a goal ?
is seeing new things a goal or something else ?
Title: Re: mini A.I investigations
Post by: kei10 on December 17, 2016, 08:56:47 pm
You asked something that had been answered already.
Title: Re: mini A.I investigations
Post by: yotamarker on December 17, 2016, 09:12:29 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 ?
Title: Re: mini A.I investigations
Post by: Art on December 19, 2016, 12:28:16 pm
(You + Prank) - Me = Humor
Title: Re: mini A.I investigations
Post by: yotamarker on December 24, 2016, 08:38:43 am
how do you think data is stored in the brain ?

arrays ? dictionary type ? lists ? stacks ?
Title: Re: mini A.I investigations
Post by: kei10 on December 24, 2016, 10:12:52 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 (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 (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 (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.
Title: Re: mini A.I investigations
Post by: yotamarker on December 24, 2016, 12:00:42 pm
that is the physical structure of the memory but not the type of memory
which could only be deduced algorithmically.
Title: Re: mini A.I investigations
Post by: Korrelan on December 24, 2016, 12:49:55 pm
Memory is the structure and vice versa.

 :)
Title: Re: mini A.I investigations
Post by: yotamarker on December 24, 2016, 12:58:26 pm
so your answer is nodes ?
Title: Re: mini A.I investigations
Post by: Korrelan on December 24, 2016, 04:29:44 pm
Quote
so your answer is nodes ?

Erm… not exactly… the neurons/ nodes are only part of the mechanism.

There are literally millions of ways to encode/ decode data in various systems.

Don’t get me started on data schemas… I could write volumes lol. So I’ll stick to a few basic examples.

Information is curious stuff… and a lot depends on how you perceive it.

You have all the stuff in your home kitchen required to build an object recogniser/ classifier at least on par if not better Google or Deepminds efforts. It will recognise any shape/ object from any orientation and utilises a kind of swam intelligence.

Have you figured it out?... a bucket of water and a measure. All objects displace a specific volume of water when submerged. A water molecule is a very simple ‘thing’, not intelligent in any way.  All it wants to do is flow… both amongst its peers and the container/ object... but billions of water molecules together encode the complex properties of the shape into one single number… the displacement volume.

As a general rule I’ve found with data representation the more dimensions you can encode the data over the better.  My simulations utilise hundreds of dimensions… that’s why parallel searches are so fast… your just searching the data from the perspective/ dimension of the search criteria.

So let’s say you have two objects that have exactly the same displacement… how to tell these apart?  Add another dimension… weight. Now use using the mass of the molecules combined to produce just one number that represents this dimension of the complete object.

Using just these two dimensions it’s possible to build the recogniser… simple eh?

How many ways could you use the cars in a car park to encode data; you could encode various levels of data using the properties of the simulation. Car mass, colour, size, style, position, rotation, etc… imagine 80 billion cars and the data patterns you could store.

I know the examples where simple and it wasn’t my intention to patronise… It’s Xmas eve and I’m enjoying the Xmas spirit lol… so I’m… not running at full capacity lol.

 :)
Title: Re: mini A.I investigations
Post by: kei10 on December 24, 2016, 08:43:06 pm
That's very interesting, for the least.
Enjoy your xmas!  ;D
Title: Re: mini A.I investigations
Post by: yotamarker on December 25, 2016, 07:32:34 pm
why does killing the final boss in video games give me a good feeling ?
for example I killed the fifth boss in kanji no owari and it feels nice
Title: Re: mini A.I investigations
Post by: kei10 on December 25, 2016, 09:26:10 pm
Bosses are expected to be difficult to beat.
When it comes to that, it's about challenge.
As you beat something challenging, you judge yourself.
Whilst you also finally able to rest from the challenge as you've completed.

Altogether with multiple factors skyrockets your feelings into something good and positive.
Therefore, you get the intense pleasure of beating those god forsaken bosses.
Title: Re: mini A.I investigations
Post by: yotamarker on January 11, 2017, 01:19:52 am
what creates the need to celebrate ?
Title: Re: mini A.I investigations
Post by: infurl on January 11, 2017, 02:47:11 am
if @yotamaker stopped posting such stupid pointless posts everyone would celebrate
Title: Re: mini A.I investigations
Post by: kei10 on January 11, 2017, 02:53:13 am
if @yotamaker stopped posting such stupid pointless posts everyone would celebrate
(https://media.giphy.com/media/GpnMx1HjMwQOQ/giphy.gif)

Infurl, rather bother writing long answers, I let's just throw in google links that could answer for him from multiple sources! That will make everyone's life easier!

Here, let me show you!

what creates the need to celebrate ?

http://lmgtfy.com/?q=what+creates+the+need+to+celebrate (http://lmgtfy.com/?q=what+creates+the+need+to+celebrate)
Title: Re: mini A.I investigations
Post by: Korrelan on January 11, 2017, 08:27:25 am
Quote
what creates the need to celebrate ?

Indoctrination and peer pressure.

Xmas used to be a violent pagan festival.  When the ‘christian religion’ arrived they tried to stop the yearly festival; but because it was so much fun people wouldn’t give it up.  They solved the problem by hijacking the dates for their own uses.

Xmas was actually banned in America until 1820.

https://www.youtube.com/watch?v=0lzVZ1lWu-w (https://www.youtube.com/watch?v=0lzVZ1lWu-w)

 :)
Title: Re: mini A.I investigations
Post by: yotamarker on January 11, 2017, 10:23:11 am
if @yotamaker stopped posting such stupid pointless posts everyone would celebrate

I'm so sorry for wasting your precious time you must have some
important brain surgery level stuff to do, I mean if you R so smart we
should use your AGI you do have one right you talk like you do.

(https://i.imgflip.com/1hgapr.jpg) (https://imgflip.com/i/1hgapr) (https://imgflip.com/memegenerator)

getting back to business,
what kinds of celebrations are there ?
what triggers them ?
Title: Re: mini A.I investigations
Post by: kei10 on January 11, 2017, 12:26:05 pm
what kinds of celebrations are there ?
what triggers them ?
https://en.wikipedia.org/wiki/List_of_holidays_by_country (https://en.wikipedia.org/wiki/List_of_holidays_by_country)

Additionally, I do believe the wording "What triggers them" is almost interchangeable from "What creates the need to celebrate" from this matter of subject...

"In older times where only library exists, where thee must rummage through the mass of tomes for the sake of wisdom."

"Now we have a wall of information, with as simple as a few clicks and key presses in front of what thee have now shalt unlock the door of knowledge to thee."

"Why bother someone with such trivial inquiry, when the answer can be much conveniently sought?"

"Thee may contend that there is no wrong to inquire from someone, but it is wrongest for persistent insignificant pestering..."

Google is your friend most of the time. Do please refrain from creating too many almost-inconsequential threads...

I do believe the admins and mods here are having tough time combing the mess of the board section...
Title: Re: mini A.I investigations
Post by: yotamarker on January 11, 2017, 02:10:57 pm
possible triggers :
date
winning of territory
birth
winning of game or election
person
social gathering

characteristics of celebration ?
Title: Re: mini A.I investigations
Post by: yotamarker on February 10, 2017, 01:23:45 am
lets say there are 2 A.Is and they have different names for the same
object so how they gonna decide the objects name ?
Title: Re: mini A.I investigations
Post by: Art on February 10, 2017, 02:18:51 am
Demonstration
Title: Re: mini A.I investigations
Post by: yotamarker on February 10, 2017, 11:00:28 am
its a puzzle with verbs also : the verb for using money is to pay

I pay for bananas
he invested in real estate
she squanders on purses

is this context sensitive ?