Computer Chess Club Archives


Search

Terms

Messages

Subject: No interdisciplinary at all, it's just about NN

Author: Christophe Theron

Date: 10:35:40 07/04/03

Go up one level in this thread


On July 04, 2003 at 04:13:13, Rolf Tueschen wrote:

>On July 03, 2003 at 13:04:25, Christophe Theron wrote:
>
>>On July 03, 2003 at 05:10:13, Rolf Tueschen wrote:
>>
>>>On July 03, 2003 at 01:54:32, Christophe Theron wrote:
>>>
>>>>On July 02, 2003 at 04:17:28, Rolf Tueschen wrote:
>>>>
>>>>>On July 01, 2003 at 18:20:12, Fernando Alonso wrote:
>>>>>
>>>>>>On July 01, 2003 at 15:46:06, Ralph Stoesser wrote:
>>>>>>
>>>>>>>Right, that's what I intend with my question. During a 'normal' chess game a
>>>>>>>chess engine has to face often positions where the difference in evaluation
>>>>>>>between let's say the 5 best moves or so is very small. In such circumstances a
>>>>>>>trained neural network maybe could help to find good positional moves better
>>>>>>>than a classical evaluation.
>>>>>>>
>>>>>>>Ralph
>>>>>>
>>>>>>I agree with you, that is the important point. To put it in other words, can I (
>>>>>>a patzer) with my little chessknowledge, beat Fritz 8 using Fritz 8 to analyze
>>>>>>the moves I my brain "thinks"?. I am sure there is a level of playing were
>>>>>>someone using a program can beat easily the same program playing alone. But can
>>>>>>that knowledge be implemented in neural networks?
>>>>>
>>>>>
>>>>>What knowledge? For the moment nobody addressed Tom's objection IMO. Chess is
>>>>>very concrete.
>>>>>
>>>>>Now what you all are saying that there existed a "knowledge" to find "good"
>>>>>positional moves. Of course our human GM have that knowledge. It is a mixture
>>>>>out of the evaluation of the very concrete position, deeper (later) consequences
>>>>>and again very concrete calculations for these _later_ positions. I dont see why
>>>>>"fuzzy" approaches should do that job better than the "classical" evaluation.
>>>>>
>>>>>What you in special are proposing is NOT a question of "knowledge" but simply
>>>>>one of cheating. You know exactly the "thought process" of a program. So you can
>>>>>always discover a difference in the evaluation of the final position. Now the
>>>>>trick is to invite the machine to go blindly for a big difference which is then
>>>>>the win for you. This is typically the approach of smart amateurs with weaker
>>>>>chess talents. [Dreihirn comes to mind.] But real chess is something else. A GM
>>>>>does NOT win because he's a clairvoyant but because his judgement (combining the
>>>>>very concrete with the general experience for the actual and then later
>>>>>positions) is "better". A weaker chessplayer has no adaequate judgement at all.
>>>>>I cant see why neural networks should have one - where should it come from? Out
>>>>>of the blue?
>>>>>
>>>>>Again, you simply didn't address Tom's objection that "sometimes" it is very
>>>>>important where your Rook is standing. Very concrete. How to handle that
>>>>>"sometimes" it is "important"?
>>>>>
>>>>>Rolf
>>>>
>>>>
>>>>
>>>>You are demonstrating an almost total ignorance of the subject you are
>>>>discussing.
>>>>
>>>>You'd better read about neural networks first, and only then allow yourself to
>>>>make comments.
>>>>
>>>>But I admit that your writing style is pleasant. Should be enough to convince
>>>>people who do not know more than you on the subject. Go ahead.
>>>
>>>
>>>You should prefer making statements about topics itself before you utter
>>>unpleasent statements against other members.
>>
>>
>>
>>I have made on topic statements by informing the readers that you don't
>>understand the topic you are talking about and that people should not rely on
>>your point of view on this particular topic.
>>
>>Yes my message was unpleasant, just as unpleasant probably it can be to read
>>nonsense expressed with authority.
>
>
>Thanks for the bully, dear Christophe. I've waited almost a day to exclude all
>exaggeration out of my possible reply, but now time has come to teach you
>certain things you've missed in your education. I'll teach you because you've
>almost asked for. You need it!
>
>Look, Christophe, when I met you in CSS during your questioning for the group I
>read a bit about you, earlier I didn't know you, and I was astonished. When
>other people and experts in CC present their vita they give all kind of personal
>records, but here you explained that your _father_ had founded a specific
>university down there "in" Africa. While you yourself, correct me if I'm wrong,
>did not even finish your studies with the usual examinations. Of course that was
>a very interesting psychological manouevering. Then I "met" you a second time
>this winter when I was in holidays and bought myself the new 'Science et Vie'
>and to my astonishment I read in an article about computerchess (with you as the
>author) mainly something about Chess Tiger, as if Tiger ever had won the Wch and
>NOT Junior or Fritz or Shredder, of course. That was again a very interesting
>psychological manouevering. You presented to the French speaking readers a
>totally twisted history of present computerchess without even mentioning the
>actual Wch.
>I give these two examples as a forword so that you can understand what I will
>now explain.
>
>Christophe, if you'd ever been a real (examined) scientist (in whatever field),
>you would have understood what my commentaries should have meant.
>
>Of course I am 1) not a GM chessplayer myself, so no high class chess expert,
>but I am 2) also no expert for neural networks, so you are quite right with your
>assumptions. But, dear Christophe, your conclusions are false!
>
>I am an examined scientist. I am a psychologist. I am an expert for "debates"
>between scientists of different fields so to speak. Now all what I did, I agree
>with you it wasn't very much, I interfered and made clear that the actual
>answers did NOT yet meet the objection made by Tom Kerrigan. That was the core
>of my own intervention. Nothing special indeed. Nothing where I had ever
>expected that a veritable CC expert and programmer could be trapped into.
>
>Now you made clear that your comment was "unpleasent". Objection, Christophe! It
>wasn't unpleasent but stupid. You then say that you made your comment because
>you wanted that the readers here do know that I am no expert for neural
>networks. Goodness gracious me! Who had told you this fairy tale that I ever was
>such an expert? In fact I never was!
>
>But you are obviously incapable of understanding why I could still make my
>comment and thus give a helpful hint into the debate. Hint: my comment did NOT
>talk about neural networks but about the _debate_ between people about chess and
>neural network. Can you understand the difference? Obviously not yet!
>
>So I can inform you about a new chapter in your education. Today you've learned
>something about interdisciplinary cooperation. Someone from psychology could
>participate in a debate between experts of computer sciences, programmers of
>chess programs and to me unknown members of CCC.
>
>This is NOTHING you should get excited about. It's simply possible. It just
>happens.
>
>I wish you good weather down there in Africa or near-by and the necessary fun
>for your work on computerchess.    :)
>
>Rolf Tueschen



I don't understand what my personal background has to do with neural networks.

There is one relationship I can see though: on this also you do not know what
you are talking about.
* My father has never founded any university.
* I have finished my studies and obtained the degree I was applying for.
* I am not the author of the Science & Vie article. I just answered a question
about chess and intelligence and it has been published as a single physical
column of text. The rest of the article is not mine.

But who cares about my personal background here???

That you must be an expert for debates, I have no dount about it. That you have
a talent for creating polemic by bringing up misinformed statements about
someone else's background, I have no doubt.

Actually I don't care if you are an expert in psychology, insect sexuality or
micromolecular astronomy.

You jumped in a discussion about neural networks and made a number of statements
that show that you don't understand the subject you are talking about.

Instead of wasting your time answering this message with even more misinformed
facts, just invest in half an hour of good reading about neural networks. Please
go to http://www.google.com, type "neural networks basics", click on the
"Search" button and look at th results.

You might find this
  http://www.generation5.org/content/2000/nnintro.asp
or this
  http://www.zsolutions.com/neural.htm
or even this
  http://www.pmsi.fr/neurin2a.htm
of interest.

But there are hundreds or thousands of pages about the topic of neural networks.

After reading this you will probably understand why your previous statements
about neural networks are wrong.



    Christophe



This page took 0.03 seconds to execute

Last modified: Thu, 07 Jul 11 08:48:38 -0700

Current Computer Chess Club Forums at Talkchess. This site by Sean Mintz.