It is currently Sat Nov 18, 2017 9:40 pm

All times are UTC - 8 hours [ DST ]




Post new topic Reply to topic  [ 153 posts ]  Go to page Previous  1 ... 4, 5, 6, 7, 8
Author Message
Offline
 Post subject: Re: Commonsense Go
Post #141 Posted: Sat May 13, 2017 10:15 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
is that what you call an offer? are you casting aspersions upon the intelligence of L19-ers? just look at the wit of ewan and alphazed (your doppleganger, by any chance?)

seeing as you come from either the first town, which i think was Ur, or the best town, which is Hossegor, you tell us.

PS. Meanwhile, back at the ranch, while updating co.odt, i came across methods i had written a year ago to attack, because that's what Alfie had to do against Lee Sedol; i'd forgotten that if all Lee's groups lived, Alfie would be behind.

So i've already answered my own question, although there are still a few details to fill in. Thanks for your help.

The road to Hell is paved with good intentions - Niels Petersen

_________________
i ink, therefore i arm

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #142 Posted: Sun May 14, 2017 9:57 am 
Dies with sente

Posts: 101
Liked others: 21
Was liked: 16
djhbrown wrote:
is that what you call an offer?


I am not interested in implementing any hand-tuned heuristic for go.
The reason I am interesting in this discussion is to see if your ideas of goal-oriented computer-go are any different than what has been tried over tens of years already. So far it seems to me like you are trying to re-invent the wheel, and just give it a different name (actually - more like three different names).
I am also open to the possibility that I may be missing something, so I am willing to stick around a little longer.


This post by alphaville was liked by: Waylon
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #143 Posted: Sun May 14, 2017 3:34 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
the "offer" solicited is not "to implement a hand-tuned heuristic" - it is a request for you to summarise. in your own words, what your Go fighting strategy is.

Fighting is my weakest point, so i am interested to see what the fighters among you have to say.

From your comment about wheel reinvention, it sounds like you haven't read any of my papers or any of the icGo documentation and are suffering from the A or ~A syndrome.

given your name, i suppose you can't be blamed for only being able to see two colours, like a Brexiteer, or the PR champions of NN vs The Rest, such as the CEO of IBM, who has an appallingly narrow-minded perspective on AI if she actually believes what she said at Davos.

But perhaps it is i who misunderstand you - perhaps you can explain in a little detail precisely which wheel it is that you think i am reinventing - and, more importantly, why you think that?

Certainly, i make no claim to absolute originality; on the contrary, i stand on the shoulders of giants such as Boole, Bartlett, De Groot, Simon, Minsky, McCarthy, Winograd, Sacerdoti, Reitman and Wilcox, and Hofstadter, in roughly chronological order. If you want to understand what it's all about, Alfie, my posts on computer-go.org and published papers and videos will give you some background.

For me, this thread is not about collecting Facebook "friends", or flogging a half-baked product, so i care not a whit whether you or anyone else sticks around or not - i post only to engage in dialogue to clarify and refine my theory. So far, the most valuable feedback i have received in two years is Kirby's request for Swim to analyse his game, which is prompting me to further develop the attack methods of CG.

Political and religious arguments are more often than not degenerate; i have no time for them. Scientific enquiry is what tickles my fancy. On the other hand, i would be interested to teach anyone who hates Maths how to like it, because i see a real need for ordinary people to be able to see through the bullshit and spin of their exploiters, which will require a revolution in education, which is what my video series "Antidote to School" is about. Needless to say, it isn't going to happen during my lifetime, and probably not during yours either. The concrete is too solidly cast, and all the indications are that it's going to get worse before it gets better, if ever. This is no time to be young and poor.
Attachment:
commoncore.jpeg
commoncore.jpeg [ 10.65 KiB | Viewed 1043 times ]

_________________
i ink, therefore i arm

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #144 Posted: Sun May 14, 2017 4:49 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
Attachment:
commonsense.jpg
commonsense.jpg [ 27.29 KiB | Viewed 1027 times ]

_________________
i ink, therefore i arm

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #145 Posted: Sun May 14, 2017 4:52 pm 
Dies with sente

Posts: 101
Liked others: 21
Was liked: 16
djhbrown wrote:
But perhaps it is i who misunderstand you - perhaps you can explain in a little detail precisely which wheel it is that you think i am reinventing - and, more importantly, why you think that?


What I think you try to do is to teach the computer to play go your way, basically coding your way to think about go in a program, more or less directly, using a lot of if/else statements.

What modern AI is about is to teach the computer how to learn by itself. In the AlphaGo case: it learns by itself from human games, then it gets even stronger by learning by itself during self-play.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #146 Posted: Sun May 14, 2017 5:37 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
alphaville wrote:
What I think you try to do is to teach the computer to play go your way, basically coding your way to think about go in a program, more or less directly, using a lot of if/else statements.
wrong. read the paper.
alphaville wrote:
What modern AI is about is to teach the computer how to learn by itself.
wrong; that is what Alfie is about, but there is more to AI than A.
alphaville wrote:
In the AlphaGo case: it learns by itself from human games, then it gets even stronger by learning by itself during self-play.
right, up to a point; that point was a few months ago, when DeepMind created anti-Alpha and played Alpha against that to produce Master.

Alpha... Master... maybe the next edition will be called Hubris?


Last edited by djhbrown on Tue May 16, 2017 4:07 am, edited 1 time in total.
Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #147 Posted: Sun May 14, 2017 6:37 pm 
Oza
User avatar

Posts: 2747
Location: Seattle, WA
Liked others: 249
Was liked: 544
KGS: oren
Tygem: oren740, orenl
IGS: oren
Wbaduk: oren
Alphaville is correct.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #148 Posted: Mon May 15, 2017 10:40 pm 
Dies with sente

Posts: 82
Liked others: 2
Was liked: 42
Rank: OGS 7 kyu
This is quite the entertaining thread here :D

_________________
I am the author of GoReviewPartner, a small software aimed at assisting reviewing a game of Go. Give it a try!

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #149 Posted: Wed May 17, 2017 2:47 am 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
new edition of draft icGo documentation available for download from https://sites.google.com/site/djhbrown2/icgo

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #150 Posted: Thu May 18, 2017 4:57 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
having just come down from the mountain-top, where i was smacked over the head by tablets of stone setting in concrete that, unlike the scurrilously rentier capitalist profiteering AGA, AGF is a noble charity, with the same tax status as other religious organisations, the Just Cause of all the hate-mail i have received over the last couple of years is finally revealed to me. Therefore, not wishing to be hung any more from a gibbet for the blasphemous crime of laisse-majeste (i am sufficiently well-hung already), the taboo words "territory" and "influence" have been excised from Swim's vocabulary, as these are sacred terms which no atheist is permitted to utter, under pain of Hobdaying, Gelding, excommunication, extirpation, and exercise-bicycles. Alpha Akhbar! swt (peace be upon her prophet PorkyPie).

Henceforth, Swim will only speak in tongues of "colour" and "shadow", as reflected in the latest editions of icGo and cg.odt, an extract from which is:

a group which has an area of at least 4, excepting dead shapes such as box 4, bulky 5, rabbity 6 and wierd 7, is strong. (note the new spelling of weird, which better reflects its pronunciation, which is a Yankee spelling (like aleph, which used be aliffe until Google got its tentacles on it) that - unlike donut, which doesn't) better reflects its pronounciation. if Webster can do it, so can i).
and who cares, apart from Lisp, whether brackets balance?

one beneficent import of the redefinition of just about everything that Mattas is that Kirby is unchained from the burden of having to choose numbers for f, g, and h as they no longer exist, even if h still does, but i'm mot going to risk leaving that important decision up to just any old hack.

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #151 Posted: Sun May 21, 2017 6:31 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
it's taken me a while, but the dawn is slowly beginning to break - not only is AGF a religious fundamentalist organisation, but almost all of my opponents these days have no commonsense whatsoever - which is probably why they play Go, since no-one with any commonsense would do so.

never mind, little things....

here's the latest rewrite of the Introduction, not uploaded yet:

Quote:
Introduction

Go teachers use a combination of language and particular moves to explain general concepts, from which students can form their own mental images, but they still cannot see clearly what the teacher sees, because a lot of the knowledge an expert has is either tacit (subconscious) or too elaborate to explain in language alone. So they often resort to the Occam's Razor of asking students to choose between 2 or 3 moves (“would you play A, B or C?”).

But where do these choices come from? They come from inside the teacher's head, not from inside the student's head.

Maybe 85% of the thoughts we think are subconscious (Damasio, 20..), so even the most empathetic and open-minded teacher cannot explain why they think what they think, because by definition the subconscious is inaccessible to the conscious.

There is thus much to be gained from endowing a machine with the ability to form and use perceptions that can be explained by visual images and narratives, so that such knowledge can be transmitted to new generations.

In principle, human teachers could be replaced by machines.- but candidate move generation is non-trivial. Contemporary master-level computer go programs such as Alphago and JueYi utilise brute-force kneejerk reaction search, albeit reactions of learned convolutional patterns to reduce the search space. This makes them impressively powerful players - better than the best humans - but their machinations are more alchemy than chemsitry, and there will need to be substantial developments of artificial neural network architectures before they can even come close to assembling a coherent thought, let alone express it.

The parallels between artificial and natural neurons run no deeper than the parallels between any kind of neuron and a transistor (Didales, 2013) - they all perform the same basic computational function of modus ponens - in the neuron's case, moderated by the principle that the louder and more frequently you shout, the more i am inclined to believe you, regardless of whether you have the faintest idea what you are talking about. Neural nets are democracy in action: the blind leading the blind.

But the science of Artificial Intelligence has more to offer than brute force - it offers the rationality of logic. Logic too is predicated upon the principle of modus ponens, which is hardly surprising, for modus ponens is the fundamental computational mechanism upon which all computational operations - such as addition, diagnosis and prognosis - are based.

The great difference between primitive computers such as Alphago -as reflective as her namesake Alf Garnet - and sophisticated thinkers like SHRDLU (Winograd, ) and Swim (Brown, ), is that the latter operate upon conceptual structures that embody aggregate information, not just mere pixels.

"Is this a dagger i see before me?" asks Macbeth. After a few million trials and errors, Alfie could answer yes or no, but she cannot learn to draw a line around the dagger., because she doesn't know in which part of the picture the dagger is. Her convolutions quite literally convolute the real-world structure depicted by an image into a convoluted mess, good for telling A from B, but not where it is.

Swim (= See what i mean) is a software model of Go commonsense, able to explain her thinking in plain English. She is described in the context of several examples:

1. a tactical problem presented by Jennie Shin of Guo Juan's Internet go school.
2. figuring out a defence to Lee Sedol's magic wedge in game 4 of his match with Alphago.
3. providing a rationale for Alphago’s move 37 in game 2 against Fan Hui
4. finding a move for Alphago that combines moyo expansion and reduction
5. finding a moyo invasion for Jue Yi that offers two ways to succeed
6. finding a move for Andrew to grind Nick down yet further
7. finding a move to rescue Kirby from drowning.

icGo is a smart online/offline playing interface / editor / advisor / player based on Swim plus a bevy of bots like Leela that serve as a jury of peers to offer a second opinion.

Top
 Profile  
 
Offline
 Post subject: The Hierarchiy of the Imagination
Post #152 Posted: Sun Aug 27, 2017 6:57 pm 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3027817

includes some debugged algorithms, some new fightback methods, and Swim's suggested move for Kirby

_________________
i ink, therefore i arm

Top
 Profile  
 
Offline
 Post subject: Re: Commonsense Go
Post #153 Posted: Wed Nov 15, 2017 6:10 am 
Lives with ko
User avatar

Posts: 245
Liked others: 12
Was liked: 30
Rank: NR
Learning to Swim: Mechanisms are described by which a model of conceptual reasoning about Go can learn new techniques from its own analyses of expert moves and assimilate expert advice.
https://papers.ssrn.com/sol3/papers.cfm ... id=3071677

Top
 Profile  
 
Display posts from previous:  Sort by  
Post new topic Reply to topic  [ 153 posts ]  Go to page Previous  1 ... 4, 5, 6, 7, 8

All times are UTC - 8 hours [ DST ]


Who is online

Users browsing this forum: Bing [Bot] and 3 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