> it flattens out, then 0.001. I have two 980TI, and the best nets take about
>>> 5 days to train (about 20 epochs on about 30M positions). The last few
>>> percent is just trial and error. Sometimes making the net wider or deeper
>>> makes it weaker. Perhaps it's just var
g the same net more than once.
>>
>> David
>>
>> > -Original Message-
>> > From: Computer-go [mailto:computer-go-boun...@computer-go.org] On
>> Behalf
>> > Of Gian-Carlo Pascutto
>> > Sent: Tuesday, August 23, 2016 12:42 AM
>>
aining the same net more than once.
>
> David
>
> > -Original Message-
> > From: Computer-go [mailto:computer-go-boun...@computer-go.org] On Behalf
> > Of Gian-Carlo Pascutto
> > Sent: Tuesday, August 23, 2016 12:42 AM
> > To: computer-go@computer-go.or
ter-go [mailto:computer-go-boun...@computer-go.org] On Behalf
> Of Gian-Carlo Pascutto
> Sent: Tuesday, August 23, 2016 12:42 AM
> To: computer-go@computer-go.org
> Subject: Re: [Computer-go] Converging to 57%
>
> On 23-08-16 08:57, Detlef Schmicker wrote:
>
> > So, if somebody is sure
I've been working on my own AlphaGo replication (code on github
https://github.com/brilee/MuGo), and I've found it reasonably easy to hit
45% prediction rate with basic features (stone locations, liberty counts,
and turns since last move), and a relatively small network (6 intermediate
layers, 32
There are situations where carefully crafting the minibatches makes sense.
For instance, if you are training an image classifier it is good to build
the minibatches so the classes are evenly represented. In the case of
predicting the next move in go I don't expect this kind of thing will make
much
On 23/08/2016 11:26, Brian Sheppard wrote:
> The learning rate seems much too high. My experience (which is from
> backgammon rather than Go, among other caveats) is that you need tiny
> learning rates. Tiny, as in 1/TrainingSetSize.
I think that's overkill, as in you effectively end up doing
The learning rate seems much too high. My experience (which is from backgammon
rather than Go, among other caveats) is that you need tiny learning rates.
Tiny, as in 1/TrainingSetSize.
Neural networks are dark magic. Be prepared to spend many weeks just trying to
figure things out. You can
On 23-08-16 08:57, Detlef Schmicker wrote:
> So, if somebody is sure, it is measured against GoGod, I think a
> number of other go programmers have to think again. I heard them
> reaching 51% (e. g. posts by Hiroshi in this list)
I trained a 128 x 14 network for Leela 0.7.0 and this gets 51.1%
-BEGIN PGP SIGNED MESSAGE-
Hash: SHA1
Hi,
good to start this discussion here. I had the discussion some times,
and we (discussion partner and me) were not sure, against which test
set the 57% was measured.
If trained and tested with kgs 6d+ dataset, it seems reasonable to
reach 57% (I
10 matches
Mail list logo
