Commonsense Go

djhbrown · **#141**

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

alphaville · **#142**

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.

djhbrown · **#143**

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 [ 10.65 KiB | Viewed 11866 times ]

djhbrown · **#144**

Attachment:

commonsense.jpg [ 27.29 KiB | Viewed 11850 times ]

alphaville · **#145**

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.

djhbrown · **#146**

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?

oren · **#147**

Alphaville is correct.

pnprog · **#148**

This is quite the entertaining thread here

djhbrown · **#149**

new edition of draft icGo documentation available for download from https://sites.google.com/site/djhbrown2/icgo

djhbrown · **#150**

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.

djhbrown · **#151**

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.

djhbrown · **#152**

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

djhbrown · **#153**

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

djhbrown · **#154**

Frank Mundas, shark hunter, wrote:

Just when you think you've got it figured out, they come along and make a fool out of you

i should have known that the elegance and simplicity of the colour and shadow map algorithms was too good to be true.

Attachment:

bordbeforeproblem.png [ 18.21 KiB | Viewed 10516 times ]

Here, three issues are revealed:
1. E15 shouldn't be a black colour-controlled point, because D15 is in atari, so shouldn't throw out a coloured arm. That's an easy fix.
2. the shape of black's big shadow doesn't look right; it's too square; it should have more of a curved shape, like the grey line for example.
3. D14 is alive, because C16 is dead, so D14 should throw an arrow into black's shadow, something like the white shape. And it should do this, regardless of whether E15 is coloured or not.

Any ideas?

djhbrown · **#155**

talking to yourself is the first sign of madness, but i'm well past that, so more talking to myself won't make any difference.

the size and strength of a cluster's shadow is clearly a function of its thickness. An unconditionally alive cluster is infinitely thick, but although that doesn't mean it casts an infinite shadow, it does mean it casts a bigger one than a weak cluster.

as unconditional life is rare, except towards the end of the game, one has to work with one's best assessment of life and death.

Swim sees obvious life and death (lad) in a simple yet logical static way, and that's good enough to start with, although clearly it is desirable to continuously reassess lad through dynamic analysis.

Operations Research (OR) substitutes data for knowledge, and quantity for quality. This is appropriate for computing the best elevation and direction in which to point a cannon, but with the notable exceptions of OR machines like Alfie, AI might be more I if it goes the route of qualitative reasoning - that's what evolution came up with, and evolution has had plenty of time to think about it, so it's probably a good idea.

The magic number 7 plus or minus 2 might suggest that 7 degrees of thickness is appropriate, but i feel that 4 is probably sufficient for practical purposes:

dead, weak, strong, and alive.

A dead cluster casts no shadow, even if, like a narcissistic poster, it can leave a bad taste in the mouth.

An alive cluster surely casts a shadow at least as big as itself, and a merely strong one a smaller shadow. This could be approximated by varying the conditions under which the shadow of an alive or strong group propagates itself: 3 for a strong cluster, but just 2 for an alive one.

A weak cluster is little better than a dead one, so the cautious player would not be too optimistic about a weak group casting any shadow at all.

Obvious lad has already been defined, so it only remains to differentiate weak from strong [group strength is already defined, but this is about cluster strength].

One eye is a bit better than none, but one swallow does not a summer make, so maybe dangosity (stones/size) is a sounder way of assessing non-alive strength qualitatively: heavy clusters are weaker than light ones.

Dangosity is a quantitative measure, but it can be sieved through a threshold to generate a qualitative value.

0.5 (= as much eyespace as stones) sounds about right.

djhbrown · **#156**

whereas Hofstadter's snowflake theory of light works for light, Go shadows are different from light shadows, because their strength falls off with distance, a bit like the way gravity does.

So recursive shadow propagation should take that into account.

If the inverse square law is good enough for Newton, maybe it's good enough for Swim too.

However, a Go board isn't a continuum like space, but a quantised chequerboard (without the Harlequin colours), so square roots of square steps doesn't make much sense in that context.

An alive cluster has much greater gravity than its first fringe of shadows, so the lowered threshold of 2 should only apply to the first iteration; and 3 to subsequent ones. This may yield shadows with a more curved than square perimeter, so they would at least look prettier.

djhbrown · **#157**

A long time ago, in a faraway place, i was sitting on the bank of a lake in France trying to undo a seized half-hitch. Unless i undid it, i wouldn't be able to move the boom up the mast, and unless i did that, i wouldn't be able to ride the borrowed windsurfer. And we had gone there especially to windsurf.

If you have ever done any sailing, you may know just how seized a knot can become, and there i was without my trusty rusty stainless steel marlin spike. It took ages and ages of wrenching this way and that, to tease the threads of the rope a fraction of a millimetre at a time.

After what felt like forever, it came apart. The friend of a friend sitting with me said "You are tetu". I didn't know what that word meant, but her tone and eyes were positive, so feeling rather pleased with myself i figured "tetu" meant "tenacious".

Later, i asked my friend what "tetu" meant. "Stubborn", she replied !

I must be stubborn, to keep on trying to explain the bleeding obvious to what feels like a seized-up brick wall of religious fanatics that their bovine god isn't the be all and end all - but there you Go - what else is there to do? And besides, i have to acknowledge that despite all my efforts i still haven't explained it adequately, because if i had, there wouldn't be all this negativity.

Swim vs Alfie

In 19nn, alien intelligences conquered Amsterdam [1] creating a flurry of excitement that spawned a forest of clones and progeny, one of whose grandchildren [2] has conquered the world, leaving old sages like Ke Jie nursing their bruises whilst the new turks dance in the spotlight of an adoring goggling mass media to the delight of Wall Street.

For sure, it's game over for Gomans, but it's only game just beginning for AIGo, for even as the New Emperor shines in the sun, the seed of a contender lurks in the dusty corner of an old backroom [3]. Few that have glimpsed it have been able to see the wood for the trees, for to those goggling at the blinding light of saturation press, the upstart just looks an old idea in new clothes that never got anywhere when it was first tried.

But Swim is not just old; it's positively geriatric, dating back about 2000 years to a bloke called Aristotle who wrote about syllogisms.

The acid test of science is experiment. Alfie has demonstrated beyond doubt that of all the bots that virtually exist, she is simply the best, in chess as well as Go. She might even be good enough to tell the difference between a cat and a child, to decide whether it's worth the risk of crashing the car by swerving violently, something that a London driver (who in their right mind drives a car in London??) studying a Go board couldn't do because he isn't looking where he is Going, which is downhill all the way, because that's the Second Law of Thermodynamics.

What kind of BorD are you?
viewtopic.php?p=227223#p227223

1. Monte-Carlo Alien Intelligence Conquers Amsterdam. https://sites.google.com/site/djhbrown2 ... yStone.doc
2. https://www.nature.com/articles/nature24270
3. https://papers.ssrn.com/sol3/papers.cfm ... id=3071677

Commonsense Go

Who is online