It is currently Wed May 24, 2017 2:33 pm

All times are UTC - 8 hours [ DST ]




Post new topic Reply to topic  [ 151 posts ]  Go to page 1, 2, 3, 4, 5 ... 8  Next
Author Message
Offline
 Post subject: Commonsense Go
Post #1 Posted: Sun Jul 24, 2016 9:56 pm 
Lives with ko
User avatar

Posts: 189
Liked others: 6
Was liked: 26
Rank: NR
https://youtu.be/Nns70047Rxo

In this video, design of software able to think and talk about Go in a
commonsense way,is described and illustrated by two examples:
1. solving a tactical problem presented by Jennie Shen of Guo Juan's
Internet go school.
2. figuring out how to respond to Lee Sedol's magic wedge in game 4 of
his match with
Alphago.

Thank you to Guo Juan for permission to reproduce Jennie Shen's
excellent lecture.
And to Walter Reitman and Bruce Wilcox for their seminal work and moral support.

_________________
i swam, therefore i hunk


This post by djhbrown was liked by: Waylon
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #2 Posted: Mon Jul 25, 2016 3:50 am 
Lives in gote

Posts: 423
Liked others: 1
Was liked: 38
Rank: KGS 5 kyu
djhbrown wrote:
https://youtu.be/Nns70047Rxo

In this video, design of software able to think and talk about Go in a
commonsense way,is described and illustrated by two examples:
1. solving a tactical problem presented by Jennie Shen of Guo Juan's
Internet go school.
2. figuring out how to respond to Lee Sedol's magic wedge in game 4 of
his match with
Alphago.

Thank you to Guo Juan for permission to reproduce Jennie Shen's
excellent lecture.
And to Walter Reitman and Bruce Wilcox for their seminal work and moral support.


Where can we download the software?


This post by Krama was liked by 2 people: Bill Spight, Bonobo
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #3 Posted: Mon Jul 25, 2016 8:38 am 
Oza

Posts: 3974
Location: North Carolina
Liked others: 393
Was liked: 651
Rank: AGA 3k
GD Posts: 65
OGS: Hyperpape 4k
Krama wrote:
Where can we download the software?
What a fascinating question :twisted:

_________________
Occupy Babel!


This post by hyperpape was liked by: Bonobo
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #4 Posted: Mon Jul 25, 2016 9:07 am 
Lives with ko

Posts: 199
Liked others: 6
Was liked: 54
Rank: KGS 3 kyu
TLDR: A 30 minutes video of computer go ideas from the 1990's.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #5 Posted: Thu Aug 11, 2016 2:45 pm 
Lives with ko
User avatar

Posts: 189
Liked others: 6
Was liked: 26
Rank: NR
Monte Carlo and DCNN leave the Go programs of the 1990s in the dust.

The basic principles of AI planning and goal-directed problem solving have been around since the 1970s, but, with the exception of Wilcox's sector lines, none of the ideas in my video have ever been implemented in any previous Go program, nor discussed in any academic paper other than my own.

The design of Commonsense Go includes new algorithms for computing territory and influence, circumscribing groups and assessing their strengths, and new deductive methods for strategic and tactical reasoning.

Unlike all other Go programs to date, it can talk about what it's thinking in plain English, so would thus be useful to people learning Go.

Alphago has the fundamental flaw that it doesn't "know" what it's doing, because neither DCNN nor Monte Carlo embodies basic commonsense intelligence of being able to construct and reason about a meaningful computational model of the dynamics of the world.

Commonsense Go does "know". It can can find a better move sequence (see board image) than Alphago did at move 79 in game 4 of its match with Lee Sedol.

Image

The program is designed, but it's up to others to turn it into software. Could it beat Alphago across the board, and with much less hardware? I think it could.

pdf version of the video, designed to be read in "dual mode" (ie, 2 pages at a time) with odd-numbered pages on the left:

http://papers.ssrn.com/sol3/papers.cfm? ... id=2818149

_________________
i swam, therefore i hunk

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #6 Posted: Thu Aug 11, 2016 3:34 pm 
Lives in sente
User avatar

Posts: 789
Liked others: 258
Was liked: 313
djhbrown wrote:
The program is designed, but it's up to others to turn it into software. Could it beat Alphago across the board, and with much less hardware? I think it could.

Then it would be worth a fortune. Self fund the development and get rich! Maybe Google would buy your company!

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #7 Posted: Thu Aug 11, 2016 10:50 pm 
Oza

Posts: 3942
Location: Cambridge, UK
Liked others: 136
Was liked: 1921
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
djhbrown wrote:
The program is designed, but it's up to others to turn it into software. Could it beat Alphago across the board, and with much less hardware? I think it could.


I think it wouldn't as you'd be making a bot similar to GnuGo. Trying to build strong bots that embody human-like reasoning about meaningful concepts has not been successful for Go. You might be able to make a useful teaching tool for weak players, but not a strong player.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #8 Posted: Thu Aug 11, 2016 11:23 pm 
Lives in gote

Posts: 424
Liked others: 29
Was liked: 136
GD Posts: 10
djhbrown you might be interest in reading this https://arxiv.org/pdf/1604.04315v2

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #9 Posted: Thu Aug 11, 2016 11:25 pm 
Tengen

Posts: 4361
Liked others: 0
Was liked: 575
djhbrown wrote:
The design of Commonsense Go includes new algorithms for computing territory and influence, circumscribing groups and assessing their strengths, and new deductive methods for strategic and tactical reasoning.


No, because what is described (in the paper, I have not viewed the video) is not influence and strength. Concepts should also be based on connection status instead of proximity sold as "influence".

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #10 Posted: Fri Aug 12, 2016 2:02 am 
Lives with ko
User avatar

Posts: 189
Liked others: 6
Was liked: 26
Rank: NR
Quote:
you'd be making a bot similar to GnuGo


no, you wouldn't. i do call it a proposal for a new Gnu Go, because i support the principles of the Gnu Foundation. But beyond that, there is no similarity between the programs whatsoever that is not also shared by Alphago and every other bot ever written to play Go. Not a single jot. If anyone can find one, do tell.

Quote:
https://arxiv.org/pdf/1604.04315v2


i agree with their observations about Alphago and Watson. Commonsense Go (CG) does not embrace all human general commonsense, which is much richer and broader; it only embraces a version of the sense about Go that is common among Go players. But it is a somewhat stylised version of that sense; for example, it includes the concepts of clusters, colour maps and shadow maps, all of which are novel. I do not know whether a pro would see what CG calls a group in quite the same way. CG would not be a candidate for the Allen AI Challenge as it cannot answer arbitrary questions. However, it does "move beyond information retrieval and into intelligent inferencing over multiple facts, concepts, and relationships to produce correct, explainable answers to these questions" - subject to the constraint that the only questions it can answer are "Why?" and "What do you think if black/white plays <here> now?".

Quote:
what is described (in the paper, I have not viewed the video) is not influence and strength. Concepts should also be based on connection status instead of proximity sold as "influence"


influence is computed as g(shadow map). group strength has one of 4 qualitative values: alive, dead, strong and weak. Colour and shadow concepts ARE based on potential connectivity, not merely proximity, as you will see if you study the algorithms more carefully.

It should be obvious that CG's perceptions of territory and influence are its perceptions, and only its perceptions. No claim is made that CG's perceptions are mathematical proofs of unconditional connectedness, but i do claim that they correlate well with what a pro would say. If you know a pro, you can ask them. I have asked 3 pros what they think of CG's reply to Lee Sedol's move 78, but have yet to receive an answer. CG can be said to "believe" that clusters are tightly connected, and groups more loosely so. If you watch the video, you will see examples of how the colour and shadow maps are iteratively computed and recomputed after dead clusters are identified. The perimeters of clusters and groups are not impenetrable walls as they are preceived without dynamic analysis. However, the metamethod does perform dynamic analysis of connection status when applying the methods "connect" and "separate".

Robert, i believe you have some ideas of your own about how to compute influence. Please apply them to the examples in the paper/video, and share the results with us, so we can see how what your ideas produce compares with what CG thinks.

_________________
i swam, therefore i hunk

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #11 Posted: Fri Aug 12, 2016 3:19 am 
Oza

Posts: 3942
Location: Cambridge, UK
Liked others: 136
Was liked: 1921
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
djhbrown wrote:
Quote:
you'd be making a bot similar to GnuGo

no, you wouldn't. i do call it a proposal for a new Gnu Go, because i support the principles of the Gnu Foundation. But beyond that, there is no similarity between the programs whatsoever that is not also shared by Alphago and every other bot ever written to play Go. Not a single jot. If anyone can find one, do tell.

Approaching the game in terms of concepts like groups.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #12 Posted: Fri Aug 12, 2016 4:02 am 
Lives in sente

Posts: 828
Liked others: 24
Was liked: 168
troll troll troll your boat gently down the stream

_________________
North Lecale


Last edited by Javaness2 on Fri Aug 12, 2016 11:54 am, edited 1 time in total.
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #13 Posted: Fri Aug 12, 2016 5:49 am 
Tengen

Posts: 4361
Liked others: 0
Was liked: 575
djhbrown, influence concepts would be an overkill to the paper's positions. It should be sufficient to assess connection and life statuses, Current Territory and updates of these after possible next moves. (I lack time for studying these in those positions. If you want to know, apply my terms to them.)

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #14 Posted: Fri Aug 12, 2016 7:03 am 
Lives in gote

Posts: 424
Liked others: 29
Was liked: 136
GD Posts: 10
Javaness2 wrote:
troll troll troll your boat gently down the stream

hmmm I don't think this is a troll thread, after all, we already 'had' someone who claim that his program can beat AlphaGo, and the admin quickly ban him, that is the real troll.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #15 Posted: Fri Aug 12, 2016 9:15 am 
Oza
User avatar

Posts: 2704
Location: Seattle, WA
Liked others: 247
Was liked: 531
KGS: oren
Tygem: oren740, orenl
IGS: oren
Wbaduk: oren
Javaness2 wrote:
troll troll troll your boat gently down the stream


Yeah, I kind of vote for not a troll... just someone who doesn't understand computer go as well as he thinks he does.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #16 Posted: Fri Aug 12, 2016 9:26 am 
Oza

Posts: 3942
Location: Cambridge, UK
Liked others: 136
Was liked: 1921
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
pookpooi wrote:
hmmm I don't think this is a troll thread

I agree: I think djhbrown genuinely believes this stuff he is saying and although he does go on a bit it's more deluded than malicious. He might point out that both cranks and eccentric geniuses are dismissed by the mainstream.
pookpooi wrote:
after all, we already 'had' someone who claim that his program can beat AlphaGo, and the admin quickly ban him, that is the real troll.

You mean Mr ARB and his GO System! which AMAZed ;-) us all!!?? You might disagree with admins banning him (I don't) but that's not trolling. And he wasn't banned for his crazy ideas about "his program can beat AlphaGo", he was banned for his insults and attacks on other users.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #17 Posted: Fri Aug 12, 2016 9:52 am 
Lives in gote

Posts: 424
Liked others: 29
Was liked: 136
GD Posts: 10
Uberdude wrote:
You mean Mr ARB and his GO System! which AMAZed ;-) us all!!?? You might disagree with admins banning him (I don't) but that's not trolling. And he wasn't banned for his crazy ideas about "his program can beat AlphaGo", he was banned for his insults and attacks on other users.

No, no, I'm not saying that admin is trolling, I mean the other one (I'm too scare to say his name cause he might find his name in google and find out he's being mention in this thread)

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #18 Posted: Fri Aug 12, 2016 10:10 am 
Lives in gote

Posts: 424
Liked others: 29
Was liked: 136
GD Posts: 10
Also DJH Brown was wrote an article "CHALLENGE OF GO" for New Scientist back in 1979 (and many more article around that time), so he's more like an old go enthusiast that the passion has been ignite by AlphaGo :)

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #19 Posted: Fri Aug 12, 2016 11:04 am 
Oza
User avatar

Posts: 2341
Liked others: 1147
Was liked: 1041
Someone who makes the effort to make a series of videos about go is hardly a troll and doesn't deserve this kind of maligning, think what you may about his work. I personally enjoyed watching some of the videos he made, and I hope this type of reception doesn't discourage him from making more.

_________________
These moves are not part of a regular dan repertoire... - Knotwilg


This post by daal was liked by 3 people: Monadology, Ortho, Waylon
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #20 Posted: Tue Aug 16, 2016 7:28 am 
Oza

Posts: 3942
Location: Cambridge, UK
Liked others: 136
Was liked: 1921
Rank: UK 4 dan
KGS: Uberdude 4d
OGS: Uberdude 7d
Here is the response of Petr Baudis (author of Pachi) on the computer-go mailing list when someone (not dhjbrown as he is muted from the list) posted this Commonsense Go document.

Quote:
I've skimmed through
the paper. It contains a high-level pseudocode for strategic planning
of a Go-playing agent. However, it unfortunately doesn't explain how
to implement the functions like influence() or how to efficiently read
out the sequences appropriate for its kill() subroutine.

From what I remember when I first started digging into GNUGo, the actual
GNUGo's implementation might be actually very similar to what the paper
describes! The trouble starts when one starts looking into the
"implementation details" and how to avoid the combinatorial explosion
of possible sequences.

I'd encourage djhbrown to look into the GNUGo general strategy code
(which is *not* just a general alpha-beta search) and consider why it
doesn't work that well in practice. I have found debugging GNUGo's
mistakes a great educational experience in the fundamental flaws of
classic engines back then.


This post by Uberdude was liked by: Waylon
Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 151 posts ]  Go to page 1, 2, 3, 4, 5 ... 8  Next

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: Google [Bot] and 6 guests


You cannot post new topics in this forum
You cannot reply to topics in this forum
You cannot edit your posts in this forum
You cannot delete your posts in this forum
You cannot post attachments in this forum

Search for:
Jump to:  
Powered by phpBB © 2000, 2002, 2005, 2007 phpBB Group