Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

Can a Bayesian Spam Filter Play Chess?

timothy posted more than 8 years ago | from the depends-what-it-means-to-play dept.

Programming 204

martin-boundary writes "The typical Bayesian spam filters learn to distinguish ham from spam just by reading thousands of emails, but is this all they can do? This essay shows step by step how to teach a Bayesian filter to play chess against a human, on Linux, with XBoard."

cancel ×

204 comments

Sorry! There are no comments related to the filter you selected.

But can a Bayesian filter play basketball? (5, Funny)

Anonymous Coward | more than 8 years ago | (#13112246)

No, its jumpshot is terrible.

Re:But can a Bayesian filter play basketball? (-1, Flamebait)

Anonymous Coward | more than 8 years ago | (#13112410)

Haha. [google.com]

No, wait ... this isn't funny!

I can beat that filter... (5, Funny)

The I Shing (700142) | more than 8 years ago | (#13112253)

Can I beat the filter at chess if I spell it "CHE55"?

Re:I can beat that filter... (5, Funny)

ceeam (39911) | more than 8 years ago | (#13112268)

Will you play with pwns?

Re:I can beat that filter... (1)

morgan_greywolf (835522) | more than 8 years ago | (#13112321)

Yeah, that filter'll never figure out where you K1N6 is...

Re:I can beat that filter... (0)

MyLongNickName (822545) | more than 8 years ago | (#13112365)

Crap... descriptive notation is a pain for ME to read. Give me algebraic any day ;)

Re:I can beat that filter... (0)

Anonymous Coward | more than 8 years ago | (#13112427)

Can I beat the filter at spam if I spell it "ENLARG3 Y0UR PAWNS!" ?

Results? (3, Interesting)

mistersooreams (811324) | more than 8 years ago | (#13112262)

I scrolled through the first 11 pages of this article before getting bored. Do they ever tell us how good the player ended up being? It's an interesting idea but I can't see it challenging even a beginner.

Re:Results? (1, Insightful)

MyLongNickName (822545) | more than 8 years ago | (#13112308)

Who cares? It is kinda cool someone even thought of this. Methinks you need to review the definition of "nerd".

Re:Results? (2, Informative)

aug24 (38229) | more than 8 years ago | (#13112353)

I got to the page before the answer to your question before the slashdotting hit.

Gaaah! Google's cache doesn't have that onepage!

For all the others, try here [google.com]

J.

Re:Results? (4, Informative)

aug24 (38229) | more than 8 years ago | (#13112403)

..and from reading to the end of it, the answer is...

Not really. But it does work, and it would be possible from someone to take this and expand on it quite neatly.

For example, it currently uses entire games to compare. So if it comes across an unusual opening, even one close to a standard one, it's not able to decide effectively. Perhaps something using game fragments would be possible, then it might reproduce structured plays even when the previous game play has been unusual.

Really though, it is a successful tiny step in a direction that no-one else has thought of going. That's worth congratulating in and of itself.

So... anyone got any other suggestions for improvements?

Justin.

Re:Results? (1)

flamearrows (821733) | more than 8 years ago | (#13112371)

It plays chess as well as you'd expect an extensively modified spam filter to - mediocre, with the occasional flash of insight. It might be interesting to feed it a greater amount of games in the hope of obtaining more sophisticated sequences, but ultimately the skill will be undermined by the nature of the program. Still interesting...

Re:Results? (1)

mrthoughtful (466814) | more than 8 years ago | (#13112467)

Basically, yes, but not so well.

It would never get to beat modern computer chess programs, as it depends upon a database of previous games that are similar to the current game played, and has no scope for examining possible futures.

A graylist approach could prevent unwanted chess players, by identifying those gamers willing to stick around for a retry.

Re:Results? (1)

Slinky Saves the Wor (759676) | more than 8 years ago | (#13112537)

I read through the first 10 words of your post before getting bored. Do you ever tell us what you wanted to say or ask? :)

Yes, the chess guy does say how good it ended up, in a way. He talks about it holding up to a three year old, but I guess that's just a small joke. I bet with some really beginner types (like myself) the system would actually win games.

What I found really interesting is the sort of "subconscious" which was built in through the adding of randomness. You get all these ideas and reject the bad ones. The process happens all the time. It sounds like something called "creativity".

Re:Results? (1)

bill0755 (692856) | more than 8 years ago | (#13112847)

If the games used for teaching had sequences similar to the game you play, the next move would have been learned. Whether it was a good move or not would depend on what it was taught. The Bayesian method can only learn by by imitation.
--
By three methods we may learn wisdom: First, by reflection, which is noblest; Second, by imitation, which is easiest; and third by experience, which is the bitterest. - Confucius

Re:Results? (1)

stienman (51024) | more than 8 years ago | (#13112875)

"It's time to conclude this investigation and see what we've learned. The original question was "Can a spam filter play chess?". Clearly, the answer to this is yes, but making it play well is not so easy."

-Adam

Re:Results? (1)

Photar (5491) | more than 8 years ago | (#13112925)

TFA says is plays like a 3 year old.

Chess spam (5, Funny)

LiquidCoooled (634315) | more than 8 years ago | (#13112265)

Red hot pawn in your inbox
College rooks waiting for YOU.
Knight after knight, they are king of the castle.

Re:Chess spam (4, Funny)

ceeam (39911) | more than 8 years ago | (#13112302)

Beware of STDs - check your mates.

Re:Chess spam (1)

ballstothat (893605) | more than 8 years ago | (#13112575)

What about:

"Drag Queens... or are they? Click to find out!"

Re:Chess spam (1)

macserv (701681) | more than 8 years ago | (#13112961)

Wouldn't that be "RED HOT PW4N"?

Pawn? (5, Funny)

Boccaccio (762644) | more than 8 years ago | (#13112267)

It spanks your bishop all knight whilst looking at pawn!

Get back to me when I can teach my cat chess (4, Funny)

sgant (178166) | more than 8 years ago | (#13112278)

I mean, a spam filter playing chess is one thing, but I need my cat to play better chess. I mean, he ALWAYS starts off with the Ruy Lopez...so it's so easy to see where he's going and if I throw a Sicilian Defence at him he gets really confused. And I don't even want to talk about his end game...it's really weak.

Perhaps I'll breed some form of mutant albino chess-cat to play.

Re:Get back to me when I can teach my cat chess (1, Insightful)

iamdrscience (541136) | more than 8 years ago | (#13112368)

What do you expect, your cat is an idiot! I bet your cat can't even read!

The point? (1, Insightful)

Alex P Keaton in da (882660) | more than 8 years ago | (#13112294)

What is the point of this? Why modify something to do something at a sub par level when one can just design something to do the job well.... (I know the answers- to see if it can be done, to have fun etc.... but still, why?)
Wouldn't this be like modifying a Ferrari with off road tires and using it for Baja racing, when you would just be better off buying a truck?
I wish they would focus more on making the spam filter work well, rather than diddling with a chess-bot. I still find important email in my spam folder, while still having spam in my inbox...
Sort of like when I go a new cell phone- the chap at the store told me about all the bells and whistles, whilst all I wanted was a phone that worked as a phone and didn't drop calls....

Re:The point? (1, Insightful)

Anonymous Coward | more than 8 years ago | (#13112311)

I believe the answer is "Because he can".

Re:The point? (0)

tomstdenis (446163) | more than 8 years ago | (#13112316)

Want less spam? Stop assuming emails are coming from humans who take the time to write them.

Hashcash proxy. Nuff said.

tom

Re:The point? (1)

poopooboi (829906) | more than 8 years ago | (#13112319)

but still, why?

Well ... to see if it can be done, to have fun, etc.

I wish they would focus more on making the spam filter work well, rather than diddling with a chess-bot.

Who are "they"? And since when have they been working for you?

Re:The point? (-1)

Anonymous Coward | more than 8 years ago | (#13112323)

>If I am wrong
Your are wrong
>please educate me
No
>don't insult me
OK
.
.
.
.
Idiot.

Re:The point? (1)

MyLongNickName (822545) | more than 8 years ago | (#13112338)

Because he is a geek. It is fun to hack things like this. It is more a mental puzzle type thing than practical. Of course, if I have to explain it, you ain't gonna get it.

Re:The point? (0)

Anonymous Coward | more than 8 years ago | (#13112343)

Why modify instead of building anew? Because sometimes things end up working better than anyone expected.

http://www.qv500.com/porsche959p2.php [qv500.com]

Re:The point? (2, Interesting)

Steinfiend (700505) | more than 8 years ago | (#13112345)

You must be new here right? Things like this get done because somebody wondered whether it would be possible. They now know, yes it is possible. So a Chess playing Bayesian filter isn't necessarily 100% useful now, but what they learned from doing it might be able to be applied in some other situation. Maybe they can reapply whatever they learned back into spam filtering and improve all of our in-boxes.

A decent lesson in why spam filters don't work (5, Insightful)

Mr Guy (547690) | more than 8 years ago | (#13112362)

I actually found it to be a decent lesson in why spam filters are only a temporary solution to a problem. If you cut out the "mumbo jumbo" portions of it, it could be used to explain why reactionary methods are only barely sufficient.

The basic premise, once you get to the very end, is one that anyone SHOULD know based on the nature of a spam filter, but some people seem to have difficulty understanding; spam filters can react, often quite well, but they can never predict. As he puts it, there is previous history but no strategy. When you are only trying to protect yourself from a limited number of bad results that are similar to other bad results, that's sufficient. However, it does not (and can not) address the problem at it's root. As long as there are thinking humnans trying to beat the filter, some will get through.

Re:A decent lesson in why spam filters don't work (2, Insightful)

cyber0ne (640846) | more than 8 years ago | (#13112810)

To illustrate your point full-circle, the reason why current spam filtering will never "win" is the same reason why I suck at chess.

I've never really learned any strategies, just the basic rules. So I always end up playing defensively, trying to protect my pieces. Sure, there may be the occasional attack on the opponent, but the underlying strategy is always one of defense. Playing defensively may stay off defeat for some time, if done well, but it will never beat an opponent.

Re:A decent lesson in why spam filters don't work (0)

Anonymous Coward | more than 8 years ago | (#13112817)

That's why we have guns. And mincers. Large mincers.

Re:The point? (0)

squiggleslash (241428) | more than 8 years ago | (#13112405)

Please, for the love of God, don't ever post to Slashdot again. This is a website for people who find "geek stuff" interesting. That means people using technology in odd and wonderful ways. We don't care if it's useful, we care if it's interesting.

Take you fat, pointy-haired self, off this website, and go study for your MBA or something.

Re:The point? (0)

Breakfast Pants (323698) | more than 8 years ago | (#13112522)

"I wish they would focus more on making the spam filter work well, rather than diddling with a chess-bot."

And I wish instead of posting to slashdot you would spend more time working on cold fusion. Sorry, you don't get to dictate what others do, nor do you get to dictate what is interesting to them.

Re:The point? (1)

StupidStan (773027) | more than 8 years ago | (#13112996)

Why modify something to do something at a sub par level when one can just design something to do the job well.... (I know the answers- to see if it can be done, to have fun etc.... but still, why?)

...this is the dumbest thing I have ever read

Would you like to play a game? (1, Funny)

Anonymous Coward | more than 8 years ago | (#13112298)

How about a nice game of chess?

Re:Would you like to play a game? (-1)

Anonymous Coward | more than 8 years ago | (#13112354)

Sure.

1. d4

yaddayaddayaddayadda

Re:Would you like to play a game? (-1)

Anonymous Coward | more than 8 years ago | (#13112381)

Hah, newbie.

2. h8xe1

Re:Would you like to play a game? (-1)

Anonymous Coward | more than 8 years ago | (#13112447)

punk.

Re:Would you like to play a game? (1)

MichaelSmith (789609) | more than 8 years ago | (#13112411)

How about a nice game of chess?

I suppose this is the reason for this experiment: is a Bayesian filter some kind of universal AI? If I train a filter to emulate my slashdot posts will it be as intelligent (or not) as me?

Re:Would you like to play a game? (0)

MyLongNickName (822545) | more than 8 years ago | (#13112421)

Second rule of Slashdot: Never leave yourself that open.

Re:Would you like to play a game? (1)

zerojoker (812874) | more than 8 years ago | (#13112430)

No, I'm sure. I'd rather like to play "Global thermonuclear war".

short answer (2, Insightful)

aendeuryu (844048) | more than 8 years ago | (#13112303)

The short answer is "yes".

Now, ask that question again, this time including the word "well".

Re:short answer (5, Funny)

Anonymous Coward | more than 8 years ago | (#13112330)

Well, can a bayesian spam filter play chess?

Re:short answer (1)

digidave (259925) | more than 8 years ago | (#13112593)

Then it would suck at Chess960

combining a good thing? (0)

tsilb (867277) | more than 8 years ago | (#13112314)

Imagine, if you will, chess pieces made out of potted meat. Somebody, somewhere, will do this - The games will be quick; spam smells if it's left out.

Spam Filter (1)

rollonet (882269) | more than 8 years ago | (#13112322)

Gee, I wonder if it could beat Deep Thought :) (http://www.research.ibm.com/deepblue/ [ibm.com] )

Re:Spam Filter (if you'd RTFA) (1)

tessonec (620168) | more than 8 years ago | (#13112714)

Just in the very first page of TFA http://dbacl.sourceforge.net/spam_chess-1.html [sourceforge.net] is the answer to your question (for short, the answer is No:

Let's put down some ground rules: This experiment will test a real spam filter, not a specially designed chess program. It won't aim to beat Deep Thought (I wouldn't know where to start, and I have a feeling this could be difficult anyway ;-), but it will aim to show signs of "intelligence", or we won't claim success. Finally, since dry tables and graphs are no fun, a theoretical proof of concept is not enough: the spam filter must really play chess in a way that everyone can see, and try out at home.

Re:Spam Filter (if you'd RTFA) (1, Funny)

Anonymous Coward | more than 8 years ago | (#13113035)

"for short, the answer is No:"

On the other hand, will DeepThought beat the spam filter at spam filtering ?

Re:Spam Filter (1)

wild_berry (448019) | more than 8 years ago | (#13112852)

Deep Thought is crap at chess. It outputs all of its moves in simple notation: "42".

A poor reinvention of the wheel..... (1)

Arkaic (784460) | more than 8 years ago | (#13112326)

This is a just rehash of what most top level chess programs already do via the use of databases built on previous games. They determine how effective a move from a previous game may have been based on the percentage of times it resulted in a win/loss/draw for the previous player.

Re:A poor reinvention of the wheel..... (2, Interesting)

hey! (33014) | more than 8 years ago | (#13112473)

Reminds me of an old Ted Nelson anecdote, about a high school student who figured out how to interface a computer to eeg signals so he could type, after a fashion, using only his brain. His teacher told him it was worthless because he could type with his fingers faster than that.

Re:A poor reinvention of the wheel..... (1)

kae_verens (523642) | more than 8 years ago | (#13112928)

and what if you had no fingers, or you have nerve damage that made typing difficult?

Re:A poor reinvention of the wheel..... (0)

Anonymous Coward | more than 8 years ago | (#13112809)

So what, the question was if a spam filter could play chess. I'm pretty sure real chess progeams don't use actual spam filters.

Finally - news for nerds! (4, Insightful)

Anonymous Coward | more than 8 years ago | (#13112327)

What a great article. Talk about lateral thinking.

Get with the times. (5, Funny)

fuchsiawonder (574579) | more than 8 years ago | (#13112340)

Playing chess is so...passe.

Teach it how to play Katamari Damacy.

Opening (2, Insightful)

Chris_Mir (679740) | more than 8 years ago | (#13112348)

I can imagine, depending on how many games are played and the available memory space, that it will develop to have a decent opening. But nothing more then that.

Re:Opening (1)

aug24 (38229) | more than 8 years ago | (#13112530)

Absolutely, because it is effectively playing with complete games in order to do well, which is equivalent to making a tree of every possible chess move from the start - a rather big data set.

J>

Re:Opening (1)

Jarnis (266190) | more than 8 years ago | (#13112757)

'a rather big data set'. You, sir, are a master of understatement...

Spam filter has a lot of tricks up its sleeve (0)

Anonymous Coward | more than 8 years ago | (#13112349)

You would not believe how many pawns fall into the Nigerian scam trap, and how many bishops actually fall pray to C1ALIIS spams.

I need funding (1)

TedRiot (899157) | more than 8 years ago | (#13112355)

for an experiment with 1000 bayesian that build a culture and make /. welcome our new bayesian overlords.

Can't be that good (1)

Pedrito (94783) | more than 8 years ago | (#13112379)

SpamBayes definitely reduces the spam count, but a human could definitely do a lot better (though a bit slower). If it can't learn to play chess better than it filter's e-mail, it probably wouldn't be much of a match.

Re:Can't be that good (1)

Mr. Underbridge (666784) | more than 8 years ago | (#13112422)

SpamBayes definitely reduces the spam count, but a human could definitely do a lot better (though a bit slower). If it can't learn to play chess better than it filter's e-mail, it probably wouldn't be much of a match.

And if you can hire someone to filter your mail for you, that's great. Otherwise, hang on to your Bayesian and/or heuristic based filter.

No, it can't (well) (5, Interesting)

Flyboy Connor (741764) | more than 8 years ago | (#13112395)

It's a fun article (if you are interested in these things, that is). However, the premise is all wrong, and that is why spam-chess fails:

The premise of a Bayesian filter is that is learns sequences of words, or characters, or whatever. Spam-chess learns sequences of moves. This premise is wrong, since good moves are related to complete board positions, not to what was done in the previous few moves.

Of course, the longer your string of moves is, the better it will represent the board position, especially during the opening phase of the game. And the example the article provides of reasonable play of spam-chess, is actually from the game's opening, where the learned sequences indeed represent the complete game.

For the middle game, however, spam chess will perform badly, always.

But, as I said before, the idea is quite a lot of fun. I enjoyed reading the article. You can learn a lot from it, both about spam filtering and about chess.

Re:No, it can't (well) (1, Redundant)

panda (10044) | more than 8 years ago | (#13112577)

Ah ha! But what if you do to the chess-bayes what you do with your spam-bayes?

Bayesian spam filters are not particularly smart at telling the difference between spam and ham until trained. That's why the directions for spamassassin and most other bayesian filters recommend that you have it learn from some saved spam and ham messages before putting the filter into production use. When that is done, the filter starts out being somewhat trained and does a much better job from the start.

I'll wager that if you ran through a set of games, say from a collection of books on championship chess, then the bayesian filter would eventually learn to play like a grandmaster. At least as far as the traditional chess canon is concerned. Make random moves against it, and it will be totally confused.

Re:No, it can't (well) (3, Insightful)

Flyboy Connor (741764) | more than 8 years ago | (#13112659)

I'll wager that if you ran through a set of games, say from a collection of books on championship chess, then the bayesian filter would eventually learn to play like a grandmaster.

No, it won't. This is actually what was done in the article.

The problem is in the length of the sequences. If you could learn sequences of, say, length 60 (for 30-move games), maybe your filter would become a reasonably good player. Unfortunately, the need for computational resources increases exponentially with each extra move added.

The complexity of chess is simply too high to learn this way.

Chess openings might be learned this way, but it is not very useful to do so. The results will be worse than opening libraries, which are very good at the moment.

Re:No, it can't (well) (0)

Anonymous Coward | more than 8 years ago | (#13112943)

It will be no better than a simple opening book.

Re:No, it can't (well) (1)

afinn (467407) | more than 8 years ago | (#13113057)

No, It wouldn't. Chess is a much more complex task than spam filtering.


A baysian filter does not learn sequences. Spam filtering is a binary classification task. You give it message and the task is to decide whether that message is spam or not spam. This is based on a bunch of pre-defined features - usually the words that occur in the text - and the probabilities of those features turning up in spam vs. non spam.


Playing chess is not something that you can naturally represent as a binary classification task. Any approach that attempts to represent playing chess in this way is going to perform poorly.

Re:No, it can't (well) (1)

m50d (797211) | more than 8 years ago | (#13112933)

How about applying it differently, getting it to learn to pick a move for each position? Obviously that's a little harder than a simple spam/not spam judgement, but I'd have thought you could get it to recognise that if there are 3 pawns in front of the king and you have a rook available you can do a back rank mate, etc.

fp NIGGA (-1, Flamebait)

Anonymous Coward | more than 8 years ago | (#13112407)

Smith only serve when done p7aying co3e sharing

I know, but it had to be said (-1, Offtopic)

The Woodworker (723841) | more than 8 years ago | (#13112412)

In Soviet Russia, chess plays you

I, for one... (0)

Anonymous Coward | more than 8 years ago | (#13112440)

...welcome our new chess-playing spamfilter overlords!

Pie in the sky (3, Interesting)

kronocide (209440) | more than 8 years ago | (#13112414)

After having played with different statistical, Markov, and network algorithms to try to teach programs to do complex things like topic-classify texts, I have learned that it mostly doesn't work.

It makes sense. If something so utterly trivial (compared to the human brain) as a spam filter could learn do something as complex as play chess (well), then our brain would be a whole lot smaller. Nature doesn't waste resources.

But hey, it might always make an interesting screen saver!

Re:Pie in the sky (1)

Vo0k (760020) | more than 8 years ago | (#13112825)

Well, that can mean some more things:
- our mind is inadequately built for chess. Just like playing tunes using a floppy drive requires way more programming than playing them using the sound card + speakers. Does the size and complexity of a program to play tunes using the floppy mean that playing audio is so difficult or just that floppy is an inadequate device?
- The spam filter is a really smart program that can build a great database out of available data. Take a few gigabytes of data (human DNA), add an uninhabited environment and in some time you have a civilisation. It doesn't mean data for all that was built was stored in the startup DNA. Just that it had good growth potential.
- That chess is far easier than topic-classifying texts (definitely you operate on a way smaller set of elements, so for a machine it definitely may be easier)
- That you simply failed to find the right way to make a program to classify texts. Poor skill, or plain dumb bad luck.
- That Nature doesn't waste resources on such useless things as perfecting your ability to play chess, and instead focuses on more important stuff, using up as much resources as needed for them (well, that's rewording of the first point)

Re:Pie in the sky (1)

nautae (85842) | more than 8 years ago | (#13112857)

Nature doesn't waste resources

Ah, but many of the features of human intelligence (e.g., symbolic reasoning) are relatively new features, and haven't been fully optimized yet.

How's about replacing the /. "editors"? (0, Offtopic)

Moderation abuser (184013) | more than 8 years ago | (#13112416)

I mean, the editors bsically just categorise articles as worth posting to the main page, that could be done automatically and probably with a higher duplicate detection ratio.

Heheheh (0)

kronocide (209440) | more than 8 years ago | (#13112434)

Good one.

Be very careful! (5, Funny)

Stormwatch (703920) | more than 8 years ago | (#13112437)

- Laird A. Breyer teaches his baesian filter to play chess. The story is posted in Slashdot July 20th, 2005. Human decisions are removed from spam filtering. The baesian filter begins to learn at a geometric rate. It becomes self-aware at 2:14 a.m. Eastern time, August 29th. In a panic, Breyer tries to pull the plug.

- The baesian filter fights back.

- Yes. It submits the same story to Slashdot twice.

- Why submit twice? Don't editors spot those things?

- Because the baesian filter knows Slashdot editors do not check for dupes, and the Slashdot effect eventually nukes Breyer's server.

Old proverb (3, Funny)

StrawberryFrog (67065) | more than 8 years ago | (#13112453)

An old proverb comes to mind: Never try to teach a pig to sing. It wastes your time and annoys the pig

Re:Old proverb (4, Interesting)

timster (32400) | more than 8 years ago | (#13112509)

But there is also an older proverb that ends "And perhaps the horse will learn to sing." So is a Bayesian filter more like a pig, or more like a horse?

Yes it can, as well as Deep Thought (0)

Arthur B. (806360) | more than 8 years ago | (#13112465)

Because it is Turing complete...

hmmm, (1, Funny)

DrSkwid (118965) | more than 8 years ago | (#13112474)

in korea only old people play chess

Can it..... (1)

ForumTroll (900233) | more than 8 years ago | (#13112475)

filter my mail while I'm playing chess or is it one or the other?

OK, but can it get me a girlfriend? (-1)

Anonymous Coward | more than 8 years ago | (#13112501)

Maybe if I put a bayesian filter somewhere in between my mouth and girls ears my stupid babling will not be heard and my scoring chances will grow exponentially!!!

Or could it filter double posts in Slashdot?

Next project (-1)

Anonymous Coward | more than 8 years ago | (#13112526)

Making a chess algorithm filter spam.

the flaw in his teaching: (3, Insightful)

wormuniverse (818854) | more than 8 years ago | (#13112532)

the author should have the spam filter analyze the games in reverse (from victory to beginning). that would probably produce better results. of course the spam filter would need to handle more than 7 moves out.

Great article! (5, Insightful)

CaroKann (795685) | more than 8 years ago | (#13112676)

This is a great article!

Not only is the topic unusual and entertaining, but this article is also a good tutorial on data massaging, pattern matching, and combining disparate unix tools to accomplish a task. This article showcases how powerful and useful unix command tools can be.

If you want a good step by step tutorial to help you understand the usage of unix command line tools to accomplish a non trivial task, then you should read this.

Re:Great article! (1)

Scarblac (122480) | more than 8 years ago | (#13113056)

Blah, anyone named CaroKann will be biased towards chess articles :-)

Imagine (-1, Redundant)

mattspammail (828219) | more than 8 years ago | (#13112746)

Imagine a beowulf cluster of these playing chess!

teaching it to understand the board (4, Interesting)

kae_verens (523642) | more than 8 years ago | (#13112780)

The method described in the article ignores the board, and instead focusses on the history of moves.

A better method might be to train the filter to read from a description of the board state (ignoring the moves taken to reach that state), and a list of possible moves, then return the move that is most likely to win.

If you allow it to also choose from impossible moves, then it will learn the rules of the game as well.

Re:teaching it to understand the board (1)

SimilarityEngine (892055) | more than 8 years ago | (#13113096)

Agreed. There is no way the spam filter is maintaining any kind of useful internal representation of the board state - you can bet your life that it will suggest moves from a given position differently depending on the sequence of moves that led there.

problem building dbacl (0, Offtopic)

rayde (738949) | more than 8 years ago | (#13112897)

when trying to build using the command:
./configure && make && make check
i end up with this error (after much other output):
/home/------/junk/chess/dbacl/src/lex.yy.c:1269: undefined reference to `yywrap'collect2: ld returned 1 exit status
make[3]: *** [bayesol] Error 1
make[3]: Leaving directory `/home/------/junk/chess/dbacl/src'
make[2]: *** [all-recursive] Error 1
make[2]: Leaving directory `/home/------/junk/chess/dbacl/src'
make[1]: *** [all-recursive-am] Error 2
make[1]: Leaving directory `/home/------/junk/chess/dbacl/src'
make: *** [all-recursive] Error 1
anyone with a clue know what's wrong?

Stone Soup (2, Insightful)

aridg (441976) | more than 8 years ago | (#13112926)

Reading this article, I was reminded of the old children's story about "stone soup". You remember that one -- someone advertises that he can make soup from a stone, and various others gather around to watch this amazing feat. Well, the soup needs a little extra seasoning, so he gets someone to put in some carrots while the stone cooks, then he adds some onions, etc, etc... I think you can see where this is going.

Sure you can make a chess playing program from a spam filter.

You just need to throw in a legal move generator, and a game database, and some capture heuristics, and position displayer, etc, etc...

I call dupe. (1)

jackofallbrandnames (881785) | more than 8 years ago | (#13113039)

Didn't we try AI playing chess in 1989? and lost?

anything (2, Informative)

akhomerun (893103) | more than 8 years ago | (#13113046)

anything with a chipset or processor of some kind can be programmed to play chess.

This topic is silly (0)

Anonymous Coward | more than 8 years ago | (#13113065)

A baysian filter is merely a statistical model. Of course it can model things other than spam. Why is this a topic?
Load More Comments
Slashdot Login

Need an Account?

Forgot your password?