On 12/16/2014 1:03 PM, "Ingo Althöfer" wrote:
Hello,
it is fantastic that mails from the list are distributed again - thanks to Petr
and to anybody else who helped with this.
One question: Is it somehow ensured that the mails will be properly archived?
At least they are not shown in the old ar
Hello,
it is fantastic that mails from the list are distributed again - thanks to Petr
and to anybody else who helped with this.
One question: Is it somehow ensured that the mails will be properly archived?
At least they are not shown in the old archive list:
http://dvandva.org/pipermail/compu
I am very much looking forward to your paper. I do see the CNN research as a
new idea that has great potential.
> Linear models like what MM is using are ... far less powerful than CNN
My mathematical objection is that this cannot be. The "no free lunch" theorem
applies, and besides, both
Hi Aja,
That being said, Hiroshi, are you sure there was no problem in your
experiment? 6% winning rate against GnuGo on 19x19 seems too low for a
predictor of 38.8% accuracy. And yes, in the paper we will show a game that
I tried without resign, but result is similar.
winrate games
19
My impression is that each feature gets a single weight in Crazy-stone. The
team-of-features aspect arises because a single point can match several
patterns, so you need a model to assign credit when tuning. The paper that I
remember used fixed receptive fields to define the patterns. (E.g., fro
