On Fri, Aug 21, 2009 at 16:13, Michael Petch
<address@hidden> wrote:
On 21/08/09 11:37 AM, "Frank Berger" <
address@hidden> wrote:
> This is absolute nonsens.
> Why? quite easy. Any NN I'm aware of is presented the position to
> evaluate it.
> Therefore it never sees the dice and can therefore not learn a pattern.
>
I agree and disagree. The NN never sees the dice - agreed. However I
believe an NN is indirectly guided by the dice. If you took the neural net
trainer and had Gnubg play itself again but this time set up the random
number source to throw away all the doubles I am pretty sure how the Bot
learns to play the game over time will change.
My opinion though is the Mersenne Twister is cryptographically strong enough
and has such a massive period that the Bot would likely not be able to see
anything (the period for standard 32 bit versions of mersenne are 2^219937 ?
1).
On a side note if one reviews the code from the old days, Mersenne Twister
was not available (Unimplemented) and the random data source could have also
been something with a considerable shorter period.
If you trained with one random number generator and then play with another
any thing the NN might have learned as a result doesn't matter. GnuBG
doesn't continue to learn while it plays humans (or have knwoledge of the
generator being used during the actual match), so it can't possible garner
knowledge from random number generators it may never have seen (or were
implemented differently).
I have read most of Roy's online postings, and his website and authoring
pages. His view on Gnubg is that it is self learning and changes as it plays
an opponent. This is his single biggest false assumption. He asked Albert
You are either directly lying or as obtuse as it gets.
I have noted that is DOES self learn WHEN THE DB IS OPEN.
Nothing else.
Please do not mis state my position again.
When you deliberate mangle an argument that way you lay yourself open to severe issues of slander:
it will harm the valid results of GNUBG if you pursue it this way, whether you win or not,.
And that will denoue the VALID results within GNUBG.
When you msiqwualified my statements of _asserted_ into _proved_ from start to finish of your original exposition,
you laid yourself open to a specific charge against the
specifics of the intentions within the GNU public license,.
I urge you to go back and review that content NOW.
Do not go down this path.
It actually does have concrete legal implications.
Not that I have the resources to pursue them:
right now I am more worried about 2 years of death threats and a specificc murder (Yoshio Nakada0 in the DC homeless community, with side ramification against a cluster of 4+ other individuals (3 injured or killed) of whichI am a member.
But:
I suspect you may find thwat the GNU group will react
DAMNED strongly if
it finds you have _intentionally_ misqualified what position I have stated.
Please do not do this again.
Bypass disenfranchisement of a member of the publci in open discussion by
directly deliberate muis-statement of the positioon as stated
using your positon ithin the group and support from members int he group
will only make the matter worse.
Diret vendetta hidden undeer a facade of respectability reverses the intent of everything GNU stands for.
Do not do so again.
Please.
Silver in 2006 if the assumption that Gnubg learns during a match was
correct. I believe since then Roy has continued to believe that the bot
continues to learn, although he's been told the contrary.