No one really knows how the most advanced algorithms work

Discussion of anything and everything relating to chess playing software and machines.

Moderators: hgm, Harvey Williamson, bob

Forum rules
This textbox is used to restore diagrams posted with the [d] tag before the upgrade.

Adam Hair
Posts: 3199
Joined: Wed May 06, 2009 8:31 pm
Location: Fuquay-Varina, North Carolina

Re: No one really knows how the most advanced algorithms wor

Post by Adam Hair » Tue Apr 11, 2017 9:37 pm

Thanks for the link!

Henk
Posts: 5481
Joined: Mon May 27, 2013 8:31 am

Re: No one really knows how the most advanced algorithms wor

Post by Henk » Tue Apr 11, 2017 10:25 pm

Neural Networks are black boxes. That's why you should not use them.

User avatar
mhull
Posts: 11827
Joined: Wed Mar 08, 2006 8:02 pm
Location: Dallas, Texas
Full name: Matthew Hull

Re: No one really knows how the most advanced algorithms wor

Post by mhull » Tue Apr 11, 2017 10:45 pm

This has been an issue from the very beginning with respect to artificial neural networks. They find patterns in training data but the programmer doesn't necessarily have any idea what the salient features of the training data are (or the useless features). This is less true of small networks but large, sophisticated NNs can be intractable for the programmer.

I still have a working copy of BrainMaker 2.0 for DOS from 1989. :)

https://calsci.com/BrainIndex.html
Matthew Hull

Stan Arts
Posts: 177
Joined: Fri Feb 14, 2014 9:53 pm
Location: the Netherlands

Re: No one really knows how the most advanced algorithms wor

Post by Stan Arts » Tue Apr 11, 2017 11:01 pm

Except for me! (But I don't know why)

jdart
Posts: 3663
Joined: Fri Mar 10, 2006 4:23 am
Location: http://www.arasanchess.org

Re: No one really knows how the most advanced algorithms wor

Post by jdart » Tue Apr 11, 2017 11:30 pm

As Arthur C. Clarke said, "Any sufficiently advanced technology is indistinguishable from magic."

--Jon

whereagles
Posts: 547
Joined: Thu Nov 13, 2014 11:03 am

Re: No one really knows how the most advanced algorithms wor

Post by whereagles » Wed Apr 12, 2017 8:18 am

Yeah.. this is a bit counter-intuituve. One would say "the programmer knows it all", but the concept of training set makes stuff quite murky, as the algorithm calibrates in its own way.

Still, it also happens in heuristic chess engines. Do we really know why they choose this or that move?

User avatar
cdani
Posts: 2095
Joined: Sat Jan 18, 2014 9:24 am
Location: Andorra
Contact:

Re: No one really knows how the most advanced algorithms wor

Post by cdani » Wed Apr 12, 2017 11:15 am

whereagles wrote: Still, it also happens in heuristic chess engines. Do we really know why they choose this or that move?
Only to a point, as most changes we try don't work.

BrendanJNorman
Posts: 1262
Joined: Sun Feb 07, 2016 11:43 pm
Full name: Brendan J Norman

Re: No one really knows how the most advanced algorithms wor

Post by BrendanJNorman » Wed Apr 12, 2017 11:20 am

cdani wrote:
whereagles wrote: Still, it also happens in heuristic chess engines. Do we really know why they choose this or that move?
Only to a point, as most changes we try don't work.
Says the guy with a 3200ELO monster as his creation. :lol: :wink:

Stan Arts
Posts: 177
Joined: Fri Feb 14, 2014 9:53 pm
Location: the Netherlands

Re: No one really knows how the most advanced algorithms wor

Post by Stan Arts » Wed Apr 12, 2017 12:42 pm

whereagles wrote:Yeah.. this is a bit counter-intuituve. One would say "the programmer knows it all", but the concept of training set makes stuff quite murky, as the algorithm calibrates in its own way.

Still, it also happens in heuristic chess engines. Do we really know why they choose this or that move?
Indeed. With feedback in a complex system you often get a chaotic system where the programmer knows for example the formula of a fractal, or a limited set of laws of physics but the results are a practically infinite complexity fractal, or universe.
Strangely not so easy to apply to chess. Because of it's tactical nature? Though it should only be a matter of time before pattern recognition becomes useful in computerchess now. I fool around with it from time to time where the idea ofcourse is for it to recognise tactical or big winning/losing positional themes before they are searched which can then be applied to an evaluation function. The problem is to search more than 3 nodes per second and I'm new to pattern recognition so I have no idea what I'm doing. (Read: it doesn't recognise anything.)

On a personal note I must have gotten my first book on fractals when I was 11. (For Dutch readers: Vuiks verhandelingen.) Thought I had gotten the anwsers to the universe and everything. If we knew this why wasn't it on tv and on the news every night?

Post Reply