Slashdot is powered by your submissions, so send in your scoop

 



Forgot your password?
typodupeerror
×
AI Games

Neural Network Chess Computer Abandons Brute Force For "Human" Approach 95

An anonymous reader writes: A new chess AI utilizes a neural network to approach the millions of possible moves in the game without just throwing compute cycles at the problem the way that most chess engines have done since Von Neumann. 'Giraffe' returns to the practical problems which defeated chess researchers who tried to create less 'systematic' opponents in the mid-1990s, and came up against the (still present) issues of latency and branch resolution in search. Invented by an MSc student at Imperial College London, Giraffe taught itself chess and reached FIDE International Master level on a modern mainstream PC within three days.
This discussion has been archived. No new comments can be posted.

Neural Network Chess Computer Abandons Brute Force For "Human" Approach

Comments Filter:
  • the big Computer tournaments are run by TCEC at chessdom.com - there it would be paired against other engines, of whom Komodo and Stockfish have been pretty much dominating every year since season 2 -

    truth is, all computer chess is computer vs. computer nowadays - the losses come from different evaluations of positions - then the programmers try to correct it, etc - but since all engines are running the same hardware with resources, the best performers should win -

    you can follow Season 8 (round 1b right now) here

    http://tcec.chessdom.com/live.... [chessdom.com]

    • It will lose to those computers. It only plays at around the level of GnuChess, so don't be impressed. To be honest, I'm not even sure why this is a story.
      His method of dealing with the move horizon is cool, but I'm sure someone has thought of it before (since I have, and if I thought of it, someone else surely has).
      • by ShanghaiBill ( 739463 ) on Monday September 14, 2015 @06:30PM (#50522353)

        It only plays at around the level of GnuChess, so don't be impressed.

        You should be impressed. Not by it's level of play (which is not impressive), but by the fact that it:
        1. Taught itself to play
        2. Reached FIDE Master Level in THREE DAYS.

        To be honest, I'm not even sure why this is a story.

        See #1 and #2 above.

        • It didn't teach itself to play, it searched through the move-tree to fill in a database.
          • by Anonymous Coward

            No, that is what existing high level chess programs do, and exactly what this one doesn't do. Please go and learn about what a neural network is before commenting on this story again.

        • by Ecuador ( 740021 ) on Monday September 14, 2015 @07:13PM (#50522471) Homepage

          Are we sure it did not just learn how to install and launch GnuChess?

  • like GnuChess (Score:5, Interesting)

    by phantomfive ( 622387 ) on Monday September 14, 2015 @06:06PM (#50522245) Journal
    For comparison, GnuChess also plays at an International Master level. The article says this chess engine is much slower than GnuChess.

    Humans are able to play chess at a high level because they are able to brutally prune the decision tree.....a grandmaster can quickly eliminate most moves as useless (although he/she will probably think of it in reverse terms: saying he/she quickly identified the important moves in the position). A computer that could combine that kind of pruning with the massive searching power would be ridiculously powerful. Better than our current computers by an order of magnitude.
    • Excellent post. Turns out, there has never been any doubt that AI would eventually surpass organic intelligence. I suspect they may be combined synergistically someday.

      My curiosity has always been with the human brain's ability to play really well, like top five-in-the-World chess.

      Is it likely that a player like Bobby Fischer dedicated so much of his memory to the pursuit that he was forced to sacrifice processing power elsewhere?

      • Is it likely that a player like Bobby Fischer dedicated so much of his memory to the pursuit that he was forced to sacrifice processing power elsewhere?

        I don't think so. I've looked, but never found evidence that a human brain can "fill up." I estimated once that playing chess at a top level is similar in mental dedication to learning a second language very well (based on summing the total knowledge base required to play chess at a top level. I spent a lot of time finding grandmaster explanations of how they think).

        Since around 1980 the amount of knowledge has increased, since the grandmaster opening book grows deeper and deeper.

        Excellent post.

        Thankyou, good sir. I ho

        • I've looked, but never found evidence that a human brain can "fill up."

          This short, informal, but informative film begs to differ:

          https://www.youtube.com/watch?... [youtube.com]

          • Surely it's self evident that we lose stuff, or else we'd remember everything perfectly back to when we were born.
        • Mine often fills up, when it does it sends memories to the bit bucket. Sometimes I can't make it from one room to another before it throws away what I was thinking, other times it puts the soy-sauce in the microwave rather than the fridge.
        • Excellent post.

          Thankyou, good sir. I hope you have an excellent day.

          Jesus, I've fallen into a parallel universe.

    • by rtb61 ( 674572 )

      The human succeeds because they multi-task the solution. The idea is to tackle the problem in parallel. So one part works on immediate moves, another works of mid length strategy and another works on final strategy. This is replicated to track the opposition, so their immediate moves, their mid length strategy and their final strategy. So the actual move and strategy become a composite of the outcomes of each parallel outcome and their influence upon each other. So a plan to eliminate say a critical piece,

      • I think you're right that the human multi-tasks, but I think you're not really right on where the multi-tasking really takes place. Usually thinking about tactics, strategy, and searching through the tree are discrete steps.

        The place the parallelism really takes place is when searching for what grandmasters call candidate moves. Much like you can look at a scene and immediately recognize what objects are, a grandmaster can look at a chess board and quickly see which moves are the important ones.
    • by ZeroPly ( 881915 )
      Grandmasters can play chess at a high level because they can understand the position. Understanding the position is what allows them to efficiently prune the tree. For example, if all my opponents pieces are aimed at my king-side, I'm not going to consider king-side castling, or any combination that involves king-side castling. Also, if I know that in the Yugoslav attack of the Sicilian Dragon, exchange sacrifice on c3 is normal, I don't need to think 10 moves ahead to sacrifice a rook for a knight.

      Computer
      • Computers are unable to understand positions. Take the final setup mentioned here - http://scienceblogs.com/evolut... [scienceblogs.com]

        That's a good example. You don't really explain what it mean to 'understand' a position though. I consider "understand" to merely mean "recognize which branches are prunable."

  • I'm old enough to remember when the MCP could only play chess!
  • by mark-t ( 151149 )

    Despite the fact that computers can now beat even the best human players at chess, I've always been of the opinion that beating a human at chess was not really a solved problem, because where chess programs do so by exhaustively examining millions of board combinations to make even a single move, a grand master chess player will generally contemplate but the tiniest fraction of that amount.... and they can still play chess pretty damn well. If a computer only considered as many board combinations as a gran

    • I don't think chess is a good general AI problem any more. It really has limited combinations, there are only so many games that can be played. when you get right down to it is possible, though time consuming, to just calculate all the possible games from a given position and objectively select the best move each time. One could pre-calculate all possible positions and simply program a look up table and produce the best possible outcome every time. Much like Tic-Tac-Toe can be programed. We already ef

      • One could pre-calculate all possible positions

        Shannon calculated the number of chess positions as 10 to the power 50.
        At that rate, it would take longer than the expected life of our galaxy to compute one move, even if every molecule of the earth were turned into a supercomputer.

        • 10 ^ 50? no, I don't think that's right for positions... There are only 32 possible pieces on 64 squares with most pieces having significant limits on where they could possibly be.. For instance, a bishop will always be on 1 of 32 squares and a pawn can only advance to any of 39 squares by eliminating the opponents pieces (thus weeding down the possible positions considerably) and there are a whole host of "impossible" positions which can never be reached without having broken a rule (such as when a queen

        • One could pre-calculate all possible positions

          Shannon calculated the number of chess positions as 10 to the power 50. At that rate, it would take longer than the expected life of our galaxy to compute one move, even if every molecule of the earth were turned into a supercomputer.

          So, just another engineering problem then?

    • by Mr.CRC ( 2330444 )

      We are only partly conscious of the decision making processes in our brains. That is why we think we have some sort of creative ability that AI can never match. This is most likely an error.

      Brain architecture hypothesis (vastly simplified subset model):

      sub-conscious (SC) processes --> executive function (EF) center, and rational conscious (RC) processes --> EF.

      Also, feedback paths: RC Finally, feed-forward path SC --> RC

      It is important to understand that EF is "influenced" by RC, but EF is no

      • by Mr.CRC ( 2330444 )
        Fucking editor! Para. 4 should be: "Also, feedback paths: RC RC."
        • by Mr.CRC ( 2330444 )
          Oh good grief. One last time: "Also, feedback paths: RC comes from EF, and SC comes from EF." Para. 5 is: "Finally, feed-forward path SC goes to RC."
          • by Anonymous Coward

            Would you like to start again and have another go, please?

  • by dbc ( 135354 ) on Monday September 14, 2015 @07:41PM (#50522581)

    I thought Claude Shannon https://en.wikipedia.org/wiki/... [wikipedia.org] wrote the first program to play chess. Among other things he dabbled in.

Dennis Ritchie is twice as bright as Steve Jobs, and only half wrong. -- Jim Gettys

Working...