Skip to content
 
If you can read this, either the style sheet didn't load or you have an older browser that doesn't support style sheets. Try clearing your browser cache and refreshing the page.

(The Stack)   Someone made a chess computer that actually thinks instead of trying to calculate every possible move on the board. Shall we play a game?   (thestack.com) divider line
    More: Cool, neural networks, MSC, Sebastian Thrun, search algorithms, Garry Kasparov, Imperial College London  
•       •       •

1664 clicks; posted to Fandom » on 15 Sep 2015 at 2:25 PM (5 years ago)   |   Favorite    |   share:  Share on Twitter share via Email Share on Facebook



22 Comments     (+0 »)
View Voting Results: Smartest and Funniest
 
2015-09-15 1:16:44 PM  
cgisecurity.comView Full Size
 
2015-09-15 2:37:52 PM  
It's this sticker on the back that worries me...

img.fark.netView Full Size
 
2015-09-15 2:38:50 PM  
33.media.tumblr.comView Full Size
 
2015-09-15 2:38:56 PM  
wanna' know what the computer is thinking?

F*ck, i should have stayed with checkers.  this game is too complicated and time consuming.
 
2015-09-15 2:44:47 PM  
Neural network is not thinking. And it was around like forever.
 
2015-09-15 2:48:19 PM  
403.  Interesting reading.  Would not read again.
 
2015-09-15 3:22:35 PM  

Grahor: Neural network is not thinking. And it was around like forever.


How do you figure it's not thinking?
 
2015-09-15 3:37:03 PM  
Next: pissing on a sparkplug prevents a nuclear war.
 
2015-09-15 3:37:06 PM  
Sorry subby, but the only way to win is to not play the game....
 
2015-09-15 3:41:28 PM  

Nurglitch: Grahor: Neural network is not thinking. And it was around like forever.

How do you figure it's not thinking?


Do you know what a neural network is? They don't think, they compose functions.
 
2015-09-15 3:53:49 PM  

Fubini: Nurglitch: Grahor: Neural network is not thinking. And it was around like forever.

How do you figure it's not thinking?

Do you know what a neural network is? They don't think, they compose functions.


And they won't stop, they can't be bargained with...
 
2015-09-15 4:00:44 PM  
what the hell is "thinking"?
 
2015-09-15 4:12:32 PM  

Ned Stark: what the hell is "thinking"?


Aming
 
2015-09-15 4:19:39 PM  

Grahor: Neural network is not thinking. And it was around like forever.


Eh, they are generally set up to forge operational functions from component parts in response to repeated stimuli.  That's pretty much all thinking is, in the practical sense.  If your brain is doing either much more or much less than that, you're mentally unstable/insane.

// Albeit, your brain's got a huge head start in terms of inputs and initial design, so hopefully it's better at it than any artificial network.
 
2015-09-15 6:50:53 PM  

jaybeezey: Fubini: Nurglitch: Grahor: Neural network is not thinking. And it was around like forever.

How do you figure it's not thinking?

Do you know what a neural network is? They don't think, they compose functions.

And they won't stop, they can't be bargained with...


And God help you if you need an inverse out of that biatch.
 
2015-09-15 8:48:57 PM  
Paging "Chromartie", "Chromartie" to the Chess Competition...

/are YOU Sarah Connor?
 
2015-09-15 9:56:54 PM  
atrocitynights.comView Full Size

Cheatin biatch
 
2015-09-15 11:22:10 PM  

UsikFark: Ned Stark: what the hell is "thinking"?

Aming


ergo summing

/qed
 
2015-09-16 8:43:02 AM  
So either he rediscovered MinMax, or that's a really crappy article. My money is on the latter.


FWIW, though, this kind of evaluative model was the original approach to games (and many other aspects of AI), back when cpu cycles were expensive. Then we went through a period where the hardware got so good so quickly that subtlety didn't matter; and at the same time the goal morphed from "learn something about how people think" or even "learn something more generally applicable in AI" to "just win the game". So we got entire generations of chess computers that can beat any human, but tell us absolutely nothing interesting about AI, let alone human intelligence.
 
2015-09-16 9:49:15 AM  

Fubini: Nurglitch: Grahor: Neural network is not thinking. And it was around like forever.

How do you figure it's not thinking?

Do you know what a neural network is? They don't think, they compose functions.


Okay, and why is composing functions not thinking?
 
2015-09-16 2:35:15 PM  
Chess algorithms are extremely complex. It's not so much calculating the position of pieces after every possible move but evaluating which side is winning in any given position. It would qualify for any modern definition of thinking.
 
2015-09-16 10:42:30 PM  

Nurglitch: Fubini: Nurglitch: Grahor: Neural network is not thinking. And it was around like forever.

How do you figure it's not thinking?

Do you know what a neural network is? They don't think, they compose functions.

Okay, and why is composing functions not thinking?


Well, I don't think it is.

If you think that composing functions is thinking, why don't you argue the affirmative?

I'll get you started:

f(x) = 2x
g(x) = x + 1
f(g(x)) = 2x + 2

Look... I just made a thought.
 
Displayed 22 of 22 comments

View Voting Results: Smartest and Funniest

This thread is archived, and closed to new comments.

Continue Farking




On Twitter


  1. Links are submitted by members of the Fark community.

  2. When community members submit a link, they also write a custom headline for the story.

  3. Other Farkers comment on the links. This is the number of comments. Click here to read them.

  4. Click here to submit a link.