Re: [Computer-go] Board evaluation using a convolutional neural network

[Álvaro Begué]

> Regarding 9x9, I believe Alvaro Begue has explored this idea in a way
> which perhaps would work better in a go engine. He used pachi to generate a
> database of games by playing against itself and then trained a model in a
> similar fashion to what I did. I'm not sure about the results of his
> experiments. If someone can point me to a large database of 9x9 games it
> would be easy to edit my code to do that.
>

My experience is the same: My CNN was a very poor judge of life and death.
Part of the problem is that I couldn't get Pachi to behave exactly the way
I wanted (play to maximize score; play to the bitter end, assuming
everything left after two passes is considered alive). But perhaps there is
some deeper problem, or we are just missing an important twist to make the
technique work.

Since those initial 9x9 experiments I have worked on the much easier
problem of coming up with a probability distribution for the next move, to
make sure I wasn't doing anything really wrong with the neural network. It
seems to be working well enough (48% accuracy with a very limited set of
inputs), so I think I'll switch back to trying to predict ownership and
score.

Álvaro.


On Tue, Jan 12, 2016 at 6:10 PM, Justin .Gilmer  wrote:

> Quick question: When using this mailing list, how to I explicately reply
> to a thread, so far I've just been editing the subject and sending it to
> computer-go@computer-go.org.
>
> Regarding use in a MTCS engine, I strongly suspect it would perform poorly
> in its current form. It is quite poor at life and death, especially if you
> give it situations very different from the training set. One issue with the
> method of training was I only used games which were played until the end
> (i.e. didn't end in resignation), as a result the model is extremely biased
> that large groups of stones live simply because games not ending in
> resignation tend to be close and not have large groups die.
>
> Depending on how hard it would be to integrate into a MCTS I could try it.
> My hope was that a well trained evaluator could allow for alpha beta
> pruning to be competitive with MCTS, interested to hear the groups thoughts
> on this.
>
> Regarding 9x9, I believe Alvaro Begue has explored this idea in a way
> which perhaps would work better in a go engine. He used pachi to generate a
> database of games by playing against itself and then trained a model in a
> similar fashion to what I did. I'm not sure about the results of his
> experiments. If someone can point me to a large database of 9x9 games it
> would be easy to edit my code to do that.
>
>
> -Justin
>
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Invitation:: DICTAP2016- IEEE- Turkey

[The Sixth International Conference on Digital Information & Communication Technology & its Applications (DICTAP2016)]

**CALL FOR PAPERS**

*Mevlana University, Konya, Turkey*

July 21 - 23, 2016*

The Sixth International Conference on Digital Information & Communication
Technology & its Applications (DICTAP2016)

http://sdiwc.net/conferences/dictap2016/

All registered papers will be submitted to IEEE for potential inclusion to
IEEE Xplore

The conference welcomes papers on the following (but not limited to)
research topics:

- Information Retrieval
- Information Visualization
- Web Services, Web based Application
- Web Metrics and its Applications
- Data Grids, Data and Information Quality
- Data Models for Production Systems and Services
- Data Warehouses and Data Mining
- Data, Text, and Web Content Mining
- Image Analysis and Image Processing
- Multimedia and Interactive Multimedia
- Management and Diffusion of Multimedia Applications
- Case Studies on Data Management, Monitoring and Analysis
- Mobile, Ad Hoc and Sensor
- Network Security


Important Dates:

Submission Deadline   : Open from now until June 21, 2016
Notification of Acceptance: June 30, 2016 or 4-7 weeks from the submission
date
Camera Ready Submission   : Open from now until July 11, 2016
Registration Deadline : July 11, 2016
Conference Dates  : July 21 - 23, 2016



___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Ray Tayek]

On 1/11/2016 7:10 PM, Gonçalo Mendes Ferreira wrote:
Hi, some time back I mentioned creating a program that evaluates the 
aesthetics of a game of Go. Has anyone given it some thought? I'd love 
to have a comparison between professional and amateur dan matches,

 ...

shape  should be a candidiate. it's 
frequency in a game should correspond to rank.


thanks

--
Honesty is a very expensive gift. So, don't expect it from cheap people - 
Warren Buffett
http://tayek.com/

___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

[Computer-go] Board evaluation using a convolutional neural network

[Justin .Gilmer]

Hey everyone,
  I recently trained a CNN to do board evaluation in Go. You can see the
work on github:

https://github.com/jmgilmer/GoCNN

The network was trained on 15000 professional games which didn't end in
resignation, I had the network try to predict the final ownership based on
current board position. It's really interesting to see what it learned,
although I'm not sure it would perform well as part of a go engine (it is
not great at life and death). I invite you to check out the github repo, I
have some demonstrations of the model in the README. Any
comments/criticisms/questions are most welcome, I will be working to
improve the model in the future.
Cheers!
-Justin
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Board evaluation using a convolutional neural network

[Gonçalo Mendes Ferreira]

Although it cannot replace MC simulations altogether, it *could* be used 
for more accurate prior values I suppose. Do you plan to integrate it in 
a MCTS program and see? Michi is also written in python...


Gonçalo

On 12/01/2016 21:30, Justin .Gilmer wrote:

Hey everyone,
   I recently trained a CNN to do board evaluation in Go. You can see the
work on github:

https://github.com/jmgilmer/GoCNN

The network was trained on 15000 professional games which didn't end in
resignation, I had the network try to predict the final ownership based on
current board position. It's really interesting to see what it learned,
although I'm not sure it would perform well as part of a go engine (it is
not great at life and death). I invite you to check out the github repo, I
have some demonstrations of the model in the README. Any
comments/criticisms/questions are most welcome, I will be working to
improve the model in the future.
Cheers!
-Justin



___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Josef Moudrik]

Some time ago, we (with pasky) looked into a related question of player
attribute prediction - such as territoriality, aggresivity, influence
oriented style, or strength. Project website is here:
http://gostyle.j2m.cz/

Imo you can predict/evaluate pretty much anything you get dataset for.
Aesthetics is subjective, but if there is some consistent agreement in the
dataset, the ML would find it. My guess would be, that nice games would
correlate with calm games without much fighting and honte moves.

Regards,
Josef

On Tue, Jan 12, 2016 at 6:32 AM Robert Jasiek  wrote:

> Is playing bad moves good for aesthetics? No? Then why call it
> aesthetics? Call it perfect / good play. The most "beautiful" stone is
> bad if it is dead.
>
> --
> robert jasiek
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Hendrik Baier]

I like the topic of aesthetics in gameplay. I think the focus in
previous studies in chess was more on compositions (artificial
problems) than on actual games, so the question is not whether a
player plays beautifully, but whether a problem is elegant and
beautiful. And they did come up with interesting measures - certainly
problems where bold sacrifices have to be made, weak pieces are used
effectively against strong pieces, etc are more interesting than
problems that can be solved in expectable and routine ways.
"Heuristics are successfully violated" in beautiful problems, as
Margulies writes.
Would certainly be interesting to define such metrics in Go. Problems
where the only good move violates traditional patterns or "good form"
or is in some other way surprising and interesting, as opposed to just
being hard to find because you have to think through many variations
("neither strangeness nor difficulty produces beauty"). I could
imagine measuring the distance between a heuristic evaluation (the
output of a DCNN for example) and the result of a deep search, for
example.
Many computer scientists have problems with concepts that aren't
immediately open to formalization, or even require psychological
insight, but it's worth it IMHO :)

Cheers,
Hendrik
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Nick Wedd]

On 12 January 2016 at 13:29, Ray Tayek  wrote:

> On 1/11/2016 7:10 PM, Gonçalo Mendes Ferreira wrote:
>
> Hi, some time back I mentioned creating a program that evaluates the
> aesthetics of a game of Go. Has anyone given it some thought? I'd love to
> have a comparison between professional and amateur dan matches,
>
>  ...
>
> shape  should be a candidiate. it's
> frequency in a game should correspond to rank.
>

I would be interested to see if this is true.  My own experience suggests
otherwise.  When I watch 3-dan games, and 6-dan games, I think the 6-dans
make more empty triangles. The 3-dans are using shape as a guide (for the
previous moves, as well as the move in question), while the 6-dans don't
use such heuristics, they are able to read the stuff out.

Nick

>
> thanks
>
> --
> Honesty is a very expensive gift. So, don't expect it from cheap people - 
> Warren Buffetthttp://tayek.com/
>
>
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
>



-- 
Nick Wedd  mapr...@gmail.com
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Josef Moudrik]

And do you find these "ugly yet working" moves aesthetically pleasing?

I think it all depends what do we mean by aesthetics. In my opinion, it is
not strength - the hard thing about go imo is that while the nice (shape,
..) do often work, sometimes, the ugly move works better - precisely as
Nick writes. It is probably hard to pinpoint; aesthetics could also be
discussed/defined on multiple levels:
 * nice shape moves
 * ease of uderstandability (I find professional games which are simple
aesthetically nicer than wild fights, big tenukis, or "wtf" moments that I
do not understand)
 * interesting strategic developments (e.g. comeback)
 * admiration of player heroism, fighting spirit, ...
All these are subjective points and they probably differ a lot based on the
viewer's own style and (maybe more) strength.

It would be interesting to make a questionnaire to have some base for what
do the players find nice. If we get some questions down, I am willing to
add it to the gostyle site.

Josef

On Tue, Jan 12, 2016 at 4:12 PM Nick Wedd  wrote:

> On 12 January 2016 at 13:29, Ray Tayek  wrote:
>
>> On 1/11/2016 7:10 PM, Gonçalo Mendes Ferreira wrote:
>>
>> Hi, some time back I mentioned creating a program that evaluates the
>> aesthetics of a game of Go. Has anyone given it some thought? I'd love to
>> have a comparison between professional and amateur dan matches,
>>
>>  ...
>>
>> shape  should be a candidiate. it's
>> frequency in a game should correspond to rank.
>>
>
> I would be interested to see if this is true.  My own experience suggests
> otherwise.  When I watch 3-dan games, and 6-dan games, I think the 6-dans
> make more empty triangles. The 3-dans are using shape as a guide (for the
> previous moves, as well as the move in question), while the 6-dans don't
> use such heuristics, they are able to read the stuff out.
>
> Nick
>
>>
>> thanks
>>
>> --
>> Honesty is a very expensive gift. So, don't expect it from cheap people - 
>> Warren Buffetthttp://tayek.com/
>>
>>
>> ___
>> Computer-go mailing list
>> Computer-go@computer-go.org
>> http://computer-go.org/mailman/listinfo/computer-go
>>
>
>
>
> --
> Nick Wedd  mapr...@gmail.com
> ___
> Computer-go mailing list
> Computer-go@computer-go.org
> http://computer-go.org/mailman/listinfo/computer-go
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Board evaluation using a convolutional neural network

[Justin .Gilmer]

Quick question: When using this mailing list, how to I explicately reply to
a thread, so far I've just been editing the subject and sending it to
computer-go@computer-go.org.

Regarding use in a MTCS engine, I strongly suspect it would perform poorly
in its current form. It is quite poor at life and death, especially if you
give it situations very different from the training set. One issue with the
method of training was I only used games which were played until the end
(i.e. didn't end in resignation), as a result the model is extremely biased
that large groups of stones live simply because games not ending in
resignation tend to be close and not have large groups die.

Depending on how hard it would be to integrate into a MCTS I could try it.
My hope was that a well trained evaluator could allow for alpha beta
pruning to be competitive with MCTS, interested to hear the groups thoughts
on this.

Regarding 9x9, I believe Alvaro Begue has explored this idea in a way which
perhaps would work better in a go engine. He used pachi to generate a
database of games by playing against itself and then trained a model in a
similar fashion to what I did. I'm not sure about the results of his
experiments. If someone can point me to a large database of 9x9 games it
would be easy to edit my code to do that.


-Justin
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Board evaluation using a convolutional neural network

[Ingo Althöfer]

Hi Justin,

that sounds interesting. WOPuld it be possible for you
to train an analogous CNN for 9x9 Go?

Ingo.
 
 

Gesendet: Dienstag, 12. Januar 2016 um 22:30 Uhr
Von: "Justin .Gilmer" 
An: computer-go@computer-go.org
Betreff: [Computer-go] Board evaluation using a convolutional neural network

Hey everyone,
  I recently trained a CNN to do board evaluation in Go. You can see the work 
on github:
 
https://github.com/jmgilmer/GoCNN
 
The network was trained on 15000 professional games which didn't end in 
resignation, I had the network try to predict the final ownership based on 
current board position. It's really interesting to see what it learned, 
although I'm not sure it would perform well as part of a go engine (it is not 
great at life and death). I invite you to check out the github repo, I have 
some demonstrations of the model in the README. Any 
comments/criticisms/questions are most welcome, I will be working to improve 
the model in the future.
Cheers!
-Justin
 ___ Computer-go mailing list 
Computer-go@computer-go.org 
http://computer-go.org/mailman/listinfo/computer-go[http://computer-go.org/mailman/listinfo/computer-go]
___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go

Re: [Computer-go] Go Aesthetics

[Gonçalo Mendes Ferreira]

I agree that playing strength should not be determinant for Go 
aesthetics. Of course obvious mistakes are not pleasant, but I consider 
close matches* with either close styles (symmetry) or very different 
styles more important. Lopsided or early decided matches with big 
captures, handicaps, complicated fights, comebacks, desperate invasions, 
etc are not very pleasing.


Even if it is subjective there must be things like good shape, struggle 
to get sente, fundamentals, etc that most people agree in, even if it 
makes 6d look worse than 2d. (I'm way too weak a player to notice them 
though)


* Not including MCTS programs playing for the 0.5 win.

On 01/12/2016 03:56 PM, Josef Moudrik wrote:

And do you find these "ugly yet working" moves aesthetically pleasing?

I think it all depends what do we mean by aesthetics. In my opinion, it is
not strength - the hard thing about go imo is that while the nice (shape,
..) do often work, sometimes, the ugly move works better - precisely as
Nick writes. It is probably hard to pinpoint; aesthetics could also be
discussed/defined on multiple levels:
  * nice shape moves
  * ease of uderstandability (I find professional games which are simple
aesthetically nicer than wild fights, big tenukis, or "wtf" moments that I
do not understand)
  * interesting strategic developments (e.g. comeback)
  * admiration of player heroism, fighting spirit, ...
All these are subjective points and they probably differ a lot based on the
viewer's own style and (maybe more) strength.

It would be interesting to make a questionnaire to have some base for what
do the players find nice. If we get some questions down, I am willing to
add it to the gostyle site.

Josef

On Tue, Jan 12, 2016 at 4:12 PM Nick Wedd  wrote:


On 12 January 2016 at 13:29, Ray Tayek  wrote:


On 1/11/2016 7:10 PM, Gonçalo Mendes Ferreira wrote:

Hi, some time back I mentioned creating a program that evaluates the
aesthetics of a game of Go. Has anyone given it some thought? I'd love to
have a comparison between professional and amateur dan matches,

  ...

shape  should be a candidiate. it's
frequency in a game should correspond to rank.



I would be interested to see if this is true.  My own experience suggests
otherwise.  When I watch 3-dan games, and 6-dan games, I think the 6-dans
make more empty triangles. The 3-dans are using shape as a guide (for the
previous moves, as well as the move in question), while the 6-dans don't
use such heuristics, they are able to read the stuff out.

Nick



thanks

--
Honesty is a very expensive gift. So, don't expect it from cheap people - 
Warren Buffetthttp://tayek.com/


___
Computer-go mailing list
Computer-go@computer-go.org
http://computer-go.org/mailman/listinfo/computer-go