I’ll do training on Linux for performance, and because it is so much easier to
build than on Windows. I need something I can ship to my windows customers,
that is light weight enough to play well without a GPU.
All of my testing and evaluation machines and tools are on Windows, so I can’t
e
Welll, David is making a product. Making a product is 'trooper' solution
unless you are making very specific product to a very narrow target group,
willing to pay thousands for single license
Petri
2016-02-04 23:50 GMT+02:00 uurtamo . :
> David,
>
> You're a trooper for doing this in windows. :)
Not to beat a dead horse, but big numbers aren't inherently interesting to
describe.
There are integers bigger than any integer anyone has written down in any
form. This particular integer is large, but "consumable".
I guess I get tired of the "number of atoms in the observable universe"
comparis
Robert,
Just as an aside, I really respect your attention to detail and your
insistence that proof technique follow generalizing statements about
aspects of go.
I think that the counting problems recently were pretty interesting (number
of positions versus number of games).
The engineering probl
David,
You're a trooper for doing this in windows. :)
The OS overhead is generally lighter if you use unix; even the most modern
windows versions have a few layers of slowdown. Unix (for better or worse)
will give you closer, easier access to the hardware, and closer, easier
access to halting you
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
> One possibility is that 0=loss, 1=win, and the number they are
quoting is
> sqrt(average((prediction-outcome)^2)).
this makes perfectly sense for figure 2. even playouts seem reasonable.
But figure 2 is not consistent with the numbers in section 3
The method is not likely to work, since the goal of NN training s to reduce the
residual error to a random function of the NN inputs. If the NN succeeds at
this, then there will be no signal to train against. If the NN fails, then it
could be because the NN is not large enough, or because there
I just want to see how to get 0.5 for the initial position on the board
with some definition.
One possibility is that 0=loss, 1=win, and the number they are quoting is
sqrt(average((prediction-outcome)^2)).
On Thu, Feb 4, 2016 at 3:40 PM, Hideki Kato wrote:
> I think the error is defined as th
I think the error is defined as the difference between the
output of the value network and the average output of the
simulations done by the policy network (RL) at each position.
Hideki
Michael Markefka:
:
>That sounds like it'd be the MSE as classification error of the eventual
>result.
>
That sounds like it'd be the MSE as classification error of the eventual result.
I'm currently not able to look at the paper, but couldn't you use a
softmax output layer with two nodes and take the probability
distribution as winrate?
On Thu, Feb 4, 2016 at 8:34 PM, Álvaro Begué wrote:
> I am no
I am not sure how exactly they define MSE. If you look at the plot in
figure 2b, the MSE at the very beginning of the game (where you can't
possibly know anything about the result) is 0.50. That suggests it's
something else than your [very sensible] interpretation.
Álvaro.
On Thu, Feb 4, 2016 a
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
>> Since all positions of all games in the dataset are used, winrate
>> should distributes from 0% to 100%, or -1 to 1, not 1. Then, the
>> number 70% could be wrong. MSE is 0.37 just means the average
>> error is about 0.6, I think.
0.6 in the range
Detlef Schmicker: <56b385ce.4080...@physik.de>:
>-BEGIN PGP SIGNED MESSAGE-
>Hash: SHA1
>
>Hi,
>
>I try to reproduce numbers from section 3: training the value network
>
>On the test set of kgs games the MSE is 0.37. Is it correct, that the
>results are represented as +1 and -1?
Looks cor
I re-read the relevant section and I agree with you. Sorry for adding noise
to the conversation.
Álvaro.
On Thu, Feb 4, 2016 at 12:21 PM, Detlef Schmicker wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Thanks for the response, I do not refer to the finaly used data set:
> in
Sounds similar to adversarial networks
On Thu, Feb 4, 2016, 04:50 Huazuo Gao wrote:
> Sounds like some kind of boosting, I suppose?
>
> On Thu, Feb 4, 2016 at 7:52 PM Marc Landgraf wrote:
>
>> Hi,
>>
>> lately a friend and me wondered about the following idea.
>>
>> Let's assume you have a reas
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Thanks for the response, I do not refer to the finaly used data set:
in the referred chapter they state, they have used their kgs dataset
in a first try (which is in another part of the paper referred to
being a 6d+ data set).
Am 04.02.2016 um 18:11 s
The positions they used are not from high-quality games. They actually
include one last move that is completely random.
Álvaro.
On Thursday, February 4, 2016, Detlef Schmicker wrote:
> -BEGIN PGP SIGNED MESSAGE-
> Hash: SHA1
>
> Hi,
>
> I try to reproduce numbers from section 3: traini
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi,
I try to reproduce numbers from section 3: training the value network
On the test set of kgs games the MSE is 0.37. Is it correct, that the
results are represented as +1 and -1?
This means, that in a typical board position you get a value of
1-s
Sounds like some kind of boosting, I suppose?
On Thu, Feb 4, 2016 at 7:52 PM Marc Landgraf wrote:
> Hi,
>
> lately a friend and me wondered about the following idea.
>
> Let's assume you have a reasonably strong move prediction DCNN. What
> happens if you now train a second net on the same datab
Hi,
lately a friend and me wondered about the following idea.
Let's assume you have a reasonably strong move prediction DCNN. What
happens if you now train a second net on the same database.
When training the first net, you tried to maximize the judgement value
of the expert move. But for the sec
Hello,
the "Good judgement"-site is somewhat strange.
Why do they give April 01 as closing date, when the
match will take place already in mid March?
***
Some side information: In Germany's computer go forum we
also have a forecast. So far 52 registered members gave
their vote
21 matches
Mail list logo
