The future of Human vs Computer Go in a post-AG world.

[Kirby]

Let me ellaborate what I ment while risking to go off-topic for this thread. In go there are so many other sequences to learn (dfan got what I had in mind):

• Joseki - not only corner, but edge and enclosure invasion sequences. For example, just learning the invasion sequences for a 4-3 large knight enclosure is about the same as learning a line of the Queen's Gambit Declined.
• Life and death statuses of different eye configurations. Hundreds of positions, with thousands of sequences on how to achieve ko/seki/kill/life for them.
• Middle game invasion sequences, reduction sequences etc. Which ones work depending on what outside stones who has.

Yes there are memorization in chess too. Openings notably, but also endgame techniques (Philidor position, Lucena, Trebuchets) etc. But they are more "ideas" to remember rather than exact move sequences to play.

I added emphasis to this last sentence in the quote above.

I think all of the examples you list require "ideas" rather than exact sequences in go, too.

• Joseki - Maybe you study a bunch of joseki - they give you an idea of an even result on an empty board. Often, the particular board position influences whether playing a particular joseki is a good idea. Sometimes playing outside of joseki will be a good idea.
• Life and Death - You study life and death, and come to "memorize" certain shapes, but in a real game, you often read out the sequence yourself because of the particular nuances that you'd describing.
• Invasion/reduction sequences - Again, these give you ideas of things you can do - but the strategy, choice of whether to do it, details of moves, or deviations from "standard" are all commonplace.

[Uberdude]

I agree there is a lot of knowledge in a strong Go player's brain, but I see knowledge acquired through experience of playing, doing go problems etc as different to memorisation of opening lines, which would be akin to memorising a joseki dictionary. I don't play chess (maybe 20 kyu) so perhaps my impression that this kind of learning is more common/required in chess if one wants to become strong is misguided, but that was the impression I got from a friend (about 2200 elo), and that such learning and the similar games was boring: killing an L group in the same way in a different position on move 150 is not as boring as playing the same 15 chess opening moves yet again.

As for time limits of 15 minutes in Taiwan, here in England 1 hour each is normal, and it's chess where blitz games are more common.

[dfan]

Probably all generalizations are false.

As a better chess player (2000) than go player, I feel that the memorization burdens of go are at least as high as that of chess. But that may be to some extent because I'm more fluent in chess and thus memorization is easier. For example, I find it much easier to recognize, and recall an associated best move in, a chess position, than a go position, even a local one (e.g., a joseki). I find that a chess position has a lot more "texture" (the kinds of pieces still on the board, their relation to each other, what color squares the bishops are on, etc.) and a go position is much more abstract (moving a stone over by one point is rather subtle to detect, even if it has an important effect on the position).

Time limits for both chess and go vary a lot, of course, but even in a relatively fast chess game (say, 40 minutes a side), I feel like I have time a couple of times a game to really settle in for a decent think, and generally don't feel rushed until the end of the game, whereas in go I constantly feel pressure to stay on pace and feel bad about taking 5 minutes to try to calculate something. Of course a lot of this is due just to being more comfortable playing chess.

As far as boringness goes, I will say that one big advantage of go is that every game is interesting. When I memorize pro games, I just pick one at random, and it's always exciting for me. If I picked a random top grandmaster chess game, chances are good that it would be a relatively bloodless draw.

Sorry to drift off the original topic! I'm happy to move to another subforum if desired.

[Kirby]

dfan, you're pretty active in the L19 go problem solving competition- do you feel that you're using memorization to identify the best move for your solutions? I want to see if we're on the same page with terminology.

[Bill Spight]

Yes there are memorization in chess too. Openings notably, but also endgame techniques (Philidor position, Lucena, Trebuchets) etc. But they are more "ideas" to remember rather than exact move sequences to play.

The same is true of go, as Kirby and Uberdude have said.

Unlike in go, in chess there is seldom only one correct move.

Where did you get that idea about go?

And this is where I fear computers will step in - to increase the amount of Joseki players have to memorize, having complicated positions with one right move or disaster happens.

Go players do not have to memorize joseki. In fact, they are warned against doing so. Learn joseki and lose two stones.

Let me give you a couple of -- I hope!-- enheartening experiences of my own. Once upon a time I took 3 stones from the U. S. Champion. Play started in the open corner, and he chose a complicated joseki, one that lasted well over 40 moves, and one that I had never played. As it turned out, a couple of years earlier I had studied that joseki for maybe 15 minutes. There was one tesuji that I had to learn. I suppose that he was expecting me to miss that tesuji. Anyway, it was an easy game for me because we had come out even in a big fight. But I did not memorize anything, I just learned an idea.

When I was a 2 kyu in Japan I took 4 stones from a 4 dan. In the first corner we reached a point where I knew what the book move was, but another move looked good, and I tried it out. Disaster! Fast forward 7 years, which I had spent in the U. S., and only lived where I could play go for a little more than 2 1/2 years. Back in Japan for the summer, as a weak 3 dan I am taking 4 stones from a pro (a teaching game, OC). In the first corner we reach the same position. I still want to play the same move. This time I see a tesuji for the next play after that one. So I make the same play with the new follow-up. The fighting gets complicated, but I come out OK, I think. (In fact, I am rather pleased with myself. ) During the review I expect the pro to say something about my new move, but he doesn't. A couple of weeks later I see the whole sequence that we played in a go magazine. While I was away it had become joseki.

Now being a weak three dan is no great shakes. And even now I can hardly claim to find correct play or nearly correct play most of the time. But memorize joseki? Memorize life and death? Why bother?

[dfan]

dfan, you're pretty active in the L19 go problem solving competition- do you feel that you're using memorization to identify the best move for your solutions? I want to see if we're on the same page with terminology.

No, not really. I'm certainly using pattern recognition, but I consider that to be a separate thing.

When I talk about memorization I generally mean a conscious lookup procedure. "Oh, he played that move. I'm pretty sure I have the correct reply in my stored dictionary somewhere. Let me try to retrieve it... oh, right, I play the hane and then throw in."

Pattern recognition obviously also involves having learned things, but applying it is less conscious; you reach some state and then say "This feels like the right move" or "This situation reminds me of something" and only then do you apply your knowledge.

Of course pattern recognition requires acquiring and applying knowledge just like rote memorization but it's usually not as boring.

[Kirby]

I see. I wanted to confirm, since you made this comment:

I personally think there is at least as much memorization in Go as in chess. I include not just joseki but also life and death statuses and sequences, standard middlegame sequences, endgame tesujis and values, etc. (I realize that the specific conversation here is just about openings, though).

While it's true that you can memorize life and death statuses, and pattern recognition comes into play, in a real game, I don't often feel that I'm playing based on "memorization". The same applies to middle game sequences, endgame tesujies, etc. I might recognize a pattern from experience, but it's because I already spent the time practicing and calculating during training, for example.

The exception, in my opinion, is the opening. It's very difficult for me to quantify how good something is for good or for black in the opening unless I have a pattern I've memorized to compare it to.

But for capturing, reducing, etc., I'd consider my brain activity to be much more active than just repeating a memorized sequence.

In general, I'd say that pattern matching comes into play a lot in go, but pattern matching is possible to be established due to the reading and calculation you've done in training and through game experience.

[Tapani]

Thank you guys for an interesting discussion.

Unlike in go, in chess there is seldom only one correct move.

Where did you get that idea about go?

From my own losses (ans sometimes wins) for instance.

When reviewing my own games with help of a stronger player, almost in every game there are situations that I get severly attacked by an opponent (9k players trying to kill everything). There are often attacks that dont work because there is one way to live (and leave opponent in unfavourable situation), but I cannot find it. Usually not during the game but often not even given thirty minutes after the game.

I can give examples if someone wants to see

Before someone says that the above mistakes are done earlier in the game, maybe so. But it can often can happen even when following standard sequences (like invading the 3-3 point) and opponent plays some funny moves that is either an overplay or just works with the current whole board situation.

While it's true that you can memorize life and death statuses, and pattern recognition comes into play, in a real game, I don't often feel that I'm playing based on "memorization". The same applies to middle game sequences, endgame tesujies, etc. I might recognize a pattern from experience, but it's because I already spent the time practicing and calculating during training, for example.

Emphasis mine.

I think that hits the nails head. You don't need to read out a monkey jump, 3-3 invasion etc. You know how to deal with them, and it does not feel like you are playing from memory. But you are. Many times you can see when stones are connected -- from experience -- not having to read out. The patterns are in your memory, possibly from having read out those patterns an extensive number of times already. But when learning the game (essentially trying to shortcut to that experience) you need to memorize quite a few patterns and sequences.
Chess does not have as many memorization shortcuts, instead you learn by studying games, training your pattern recognizer how good moves look like and practicing on avoiding mistakes.

So go (like much else) in Taiwan is taught by giving rote memorization assignments. Namely sequences and games to memorize.

[Kirby]

You know how to deal with them, and it does not feel like you are playing from memory. But you are. Many times you can see when stones are connected -- from experience -- not having to read out. The patterns are in your memory, possibly from having read out those patterns an extensive number of times already. But when learning the game (essentially trying to shortcut to that experience) you need to memorize quite a few patterns and sequences.

Having a pattern in your memory is not the same as memorization. Everything that you think about is in your memory to some degree.

Chess does not have as many memorization shortcuts, instead you learn by studying games, training your pattern recognizer how good moves look like and practicing on avoiding mistakes.

How is "training your pattern recognizer how good moves look like" different than gaining experience in go? I feel you call learned go techniques "memorization shortcuts", but when describing the same phenomenon in chess, you call it "training".

My opinion is that, in both games, as you gain experience, you train your pattern recognition - sure. But it's not the same as rote memorization, since every situation is different, and requires a different strategy.

If go were just a matter of memorizing a bunch of sequences, it wouldn't have taken computers this long to get good at it, eh?

[Tapani]

Chess does not have as many memorization shortcuts, instead you learn by studying games, training your pattern recognizer how good moves look like and practicing on avoiding mistakes.

How is "training your pattern recognizer how good moves look like" different than gaining experience in go? I feel you call learned go techniques "memorization shortcuts", but when describing the same phenomenon in chess, you call it "training".

My opinion is that, in both games, as you gain experience, you train your pattern recognition - sure. But it's not the same as rote memorization, since every situation is different, and requires a different strategy.

If go were just a matter of memorizing a bunch of sequences, it wouldn't have taken computers this long to get good at it, eh?

Training the pattern recognizer is the same in both games, and not rote memorization. However, in go you (or at least I) do far more often play out moves from memory rather than in chess.

Also, nobody said go was only rote memorization. What I am trying to say, is that in order to learn and play go, one has to memorize more sequences than in say chess.

To me go has two games in one. There is a top level game deciding where to invade, reduce, strengthen, build or whatever. Then there the second game the tactical execution of those options - includes playing out memorized sequences.

In chess you only have the high level part (and checking for tactics which in turn is the tedious part of chess to learn and execute).

And chess coaches don't (usually) ask students to memorize move sequences (there are opening traps - and computers find more every day, but you don't get good by memorizing those). Go coaches on the other hand routinely tell students to study and memorize move sequences. And I don't think you can get very good without knowing a large number of those.

[Shaddy]

And chess coaches don't (usually) ask students to memorize move sequences (there are opening traps - and computers find more every day, but you don't get good by memorizing those). Go coaches on the other hand routinely tell students to study and memorize move sequences. And I don't think you can get very good without knowing a large number of those.

Could this be a culture thing? I think westerners are less likely to favor memorization as a form of training (rote memorization is basically a dirty word in English), and memorization is taken for granted in China. I want to emphasize that they don't stress critical thinking skills less, they just assume that you will memorize everything in addition to learning the "big picture" lesson being taught.

[John Fairbairn]

How is "training your pattern recognizer how good moves look like" different than gaining experience in go? I feel you call learned go techniques "memorization shortcuts", but when describing the same phenomenon in chess, you call it "training".

I think I can see why tapani makes this distinction. In chess, pattern recognition makes you aware of themes (e. queen sacrifice for pawn in a castle) buy you often have to work quite hard to apply it because so many parts of the chess position are in very close proximity. There is not a single memorisable method you can take down off the shelf and use it out of the box.

In go, which is often a set of discrete positions, there are many tesuji sequences you can memorise and use out of the box once you have recognised a position where one might work. The pattern recognised forms the problem and the tesuji you use for it are separate. Both are learned but in different ways. In real-world terms, you recognise a problem: the boiler has gone out in a particular recognisable set of cirumstances (e.g. a leak from the gefurtel). You then find tools that will fix it in ways that you have learned separately.

My opinion is that, in both games, as you gain experience, you train your pattern recognition - sure. But it's not the same as rote memorization, since every situation is different, and requires a different strategy.

Saying what I have just said, but with the difference that I claim that most tesujis (the tools) can be memorised and applied by rote. Some tesujis can be quite long but still work in easily memorable steps (e.g. throw-in and squeeze in the tombstone tesuji).

If go were just a matter of memorizing a bunch of sequences, it wouldn't have taken computers this long to get good at it, eh?

That only applies if there was a good list computer programmers could refer to. We have a partial list, but it is very small. I gather programs like AlphaGo have essentially had to make their own lists very laboriously. In so doing they have created a very, very long list of recurring patterns (problem situations) to which are attached plausible solutions (tools in the form of the most useful moves detected in those recurring patterns). I don't think chess computers can operate in that manner (except in the form of endgame tables, and even they were created by brute force), so go computers have not been able to use the chess experience there. If I'm right about how the go computers work, though, in theory their lists could be consulted by (super)humans, either for look-up or memorisation - or even for brain implants!

[Kirby]

To me go has two games in one. There is a top level game deciding where to invade, reduce, strengthen, build or whatever. Then there the second game the tactical execution of those options - includes playing out memorized sequences.

What you refer to as "memorization", I'd refer to as "chunking". When you first learn go, you know only the rules and think move-by-move. As you gain experience, do problems, review games, your mind becomes aware of larger sequences/chunks that you can think of as a single unit. While some may be able to attempt to memorize chunks, a more natural process is to acquire the skill naturally through training.

The same phenomenon happens in language. At first you learn letter-by-letter. Then you get to know words. Then common phrases become apparent. As you gain proficiency, your mind chunks the information. To me, this differs greatly from memorization.

Did you memorize the phrases in your post here on L19? Or did you construct the sentences yourself? Maybe you studied English by memorizing conversations. But I hardly think it's a necessary method for learning, as there are many other ways to gain proficiency and "chunk" techniques naturally.

[Uberdude]

I think a distinction should be made between playing moves which come from memories in your brain, and memorisation. You can form memories and train your neural networks and pattern recognizers through playing games, watching pro games, doing problems, reading books, reviewing games, or rote memorisation of joseki/tesuji dictionaries. I have done very little of the latter, but plenty of the others. It wouldn't surprise me if children in Go schools in Taiwan do rather more of the latter, as Shaddy said there's a cultural difference and rote learning hasn't been fashionable in the West, or England at least, for several decades.

Does Lee Sedol have a bigger mental database of go patterns than Magnus Carlsen does of chess patterns? Quite possibly, after all Go has a larger board with more possibilities, but chess has different pieces so there is a richer variety of positions in a smaller space. How did Lee build this mental database vs Magnus? I was under the impression that if you are a 2200 chess player and want to be a 2500 chess player you need to sit down with big books of openings and memorise them, is this true? (Of course he will also have built up a large amount of knowledge from playing, doing endgame problems and so on). Because these start from the initial board the resulting games are the same and so more boring, compared to Lee Sedol doing thousands of tsumegos (which I expect he did) but I expect he did less of memorising joseki let alone whole-board fuseki dictionaries.

I also think it would be a good idea to be more explicit about what sort of sequences and chunks of knowledge from memory we are talking about. For example, if I want to connect a stone on the 2nd line I know there are several ways:

$$B
$$ . . . . . . . .
$$ . . . O X . . .
$$ . . . O X . . .
$$ . . . O X . . .
$$ . . O X a b . .
$$ . . e d c f . .
$$ ---------------

Click Here To Show Diagram Code

[go]$$B
$$ . . . . . . . .
$$ . . . O X . . .
$$ . . . O X . . .
$$ . . . O X . . .
$$ . . O X a b . .
$$ . . e d c f . .
$$ ---------------[/go]

These moves come form my brain's policy network, to take AlphaGo terminology. Is this memory, my trained pattern recognizer, experience, intuition, all of the above? Whatever we call it I wouldn't say I arrived at it through memorisation, but years of playing Go. I have come to understand pros and cons of the different choices (a is the default solid and simple move, b offers a ko to make more eyeshape and can me useful for reaching further to the right, c leaves a peep but threatens a 1st line endgame ko, d leaves a peep or 1st line sente, but maximizes eyespace so is sometimes best for living. (There's even e sometimes for a ko or f if a stone above b). Deciding which of these pros and cons is most important in the different positions that arise in a game is not something that comes from memory but is the sort of analytical thinking that makes me enjoy Go (though there are some examples which feature it, e.g. a tripod or comb group). I don't think anyone ever taught me this as a structure blob of information to memorise, though I have taught it myself in lectures. Something like "the L group is dead" is a fact I have remembered, but the actual sequences to kill I have not, though being standard applications of life-and-death principles of hanes and then placements are moves I can generate in a few seconds.

Kirby's analogy to forming sentences is one I've come across before: iirc Matthew Macfadyen 6d said his vocabulary of Go shapes is probably as big as his vocabulary of English words. This was not built up by memorising a dictionary, but reading novels from masters of the language (aka pro games).

[Kirby]

These moves come form my brain's policy network, to take AlphaGo terminology. Is this memory, my trained pattern recognizer, experience, intuition, all of the above?

Just a sidenote - I think it's interesting to compare to AlphaGo's policy network. AlphaGo has different components that make up its go-playing strength: a policy network, a value network refined through self-play, and some sort of monte-carlo playouts (OK, OK - still not through digesting the Nature paper).

Of these different components, the policy network seems most akin to "memorization", even though I still think it's technically different from memorization. The only component requiring supervised learning was the policy network, since it required input games with a "correct" answer (i.e. how well can AlphaGo guess the dan-player's next move?).

We know from the results that the policy network alone is decently strong - like low-dan level, if I recall. But to achieve greater strength, the other components like the read ahead, and the greatly-refined value network really gave the program a boost in strength.

From this perspective, I'd assume that human go players can get decently strong through some sort of "memorization" (still don't like calling it that), in order to help train their "policy networks". But to take things to the next level, active thinking and strategy are required, which require move calculations that vary from board position to board position.