Hi Detlef,
>I gave pure DCNN 54% a try against the 15 kyu version:)
did I get it right, that these 54 % were from normal 6-dan games
("normal" meaning small or no handicap)?
I think you need "Mueller High Handicap games" for feeding the CNN.
Cheers, Ingo.
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Yes, the published
http://computer-go.org/pipermail/computer-go/2015-December/008324.html
I think, you can not win this with "normal" good moves :)
You have to exploit mfgo
Detlef
Am 29.12.2015 um 15:18 schrieb "Ingo Althöfer":
> Hi Detlef,
>
>>
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
I gave pure DCNN 54% a try against the 15 kyu version:)
http://files.gokgs.com/games/2015/12/29/mfgo15kyu0-NiceGo19N.sgf
There was no pass handling, therefore filled an eye, without would
have been 133.5 loss or so :)
Detlef
Am 29.12.2015 um 11:20
Hello all,
> Martin understood computer go weaknesses, so he played to exploit them. A
> modern program
> not specifically tuned for those weaknesses would have a much more difficult
> time.
Agreed. Concerning CNN bots (like darkfores3), a natural way would be to find
some players of
That might be a stone or two difference for that software at best, no?
s.
On Dec 28, 2015 6:58 AM, "Michael Sué" wrote:
> > Remember 1998: In the US Go Congress an exhibition match
> > took place: 5-dan Martin Mueller against Many Faces of Go.
> > Martin gave 29 handicap
Remember 1998: In the US Go Congress an exhibition match
took place: 5-dan Martin Mueller against Many Faces of Go.
Martin gave 29 handicap stones - and won "handily".
29 stones - can you believe it?
ManyFaces was a top bot in those days.
In the meantime computer go strength has increased a
thöfer"
> Sent: Monday, December 28, 2015 7:07 AM
> To: computer-go@computer-go.org
> Subject: Re: [Computer-go] Those were the days ...
>
> Hello,
>
> > > Remember 1998: In the US Go Congress an exhibition match > took
> > place: 5-dan Martin Mueller against