It’s been almost 20 years since IBM’s Deep Blue supercomputer beat the reigning world chess champion, Gary Kasparov, for the first time under standard tournament rules.
Since then chess-playing computers have become significantly stronger, giving even the best human players little chance against a modern chess engine.
Now let’s talk about today’s world. Is it possible for a person to become an International Master in chess in seventy-two hours? If that’s possible, I’d be mind-blowing! 🙂 However, there is a computer that has taught itself and made this possible.
At London’s Imperial College, one student used artificial intelligence to train his computer to be one of the best chess players in the world—and it only took three days. The self-taught chess engine, known as “Giraffe”, was designed by graduate student Matthew Lai.
Computers can already squash human opponents at chess by using their great computational speed to calculate all possible moves in a game —they generally make the best possible move every time. Lai’s Giraffe solves the same problem from a different direction: it learned to play chess without knowing the rules at all.
Deep learning helps computers make sense of the world by identifying patterns in large quantities of data. Most programmers might hard-code the rules of chess into their computers, but Lai fed Giraffe millions of sample chess positions from a computer database. Before it ever played its first game, Giraffe “studied” 175 million chess positions generated this way, building its own understanding of the 1,500-year-old game.
‘Engine Battles’ – Below is the Computer Chess Rating List (CCRL) of the Top-25 chess engines:
Giraffe holds the 159th rank with the ELO of 2424. Komodo 9.2 x64 is at the first place with the rating of 3353!
Then Lai trained Giraffe at supernatural speed. He put it up against the Strategic Test Suite, a collection of 1,500 chess puzzles designed to assess a chess engine’s capabilities in a variety of situations. Giraffe ran the puzzles continuously for three days and, eventually, it scored 9,700 out of a possible 15,000 points—a score Lai says is on a par with the best chess engines in the world.
Giraffe employs a neural network to identify the best possible move in a given chess position. Such networks are a computer-friendly tool for making decisions in a manner similar to the human brain. They are already effective tools for building intelligent-seeming systems that operate in a limited space, like controlling a robot’s movements to recognize an image.
Chess, with its limited parameters that allow for fantastic complexity, presents itself as a unique testing ground for technology like this.
‘Example of nodes searched by depth-limited search vs probability-limited search’
Giraffe’s algorithm processes all of chess as three “input layers.”
- the state of the game at large: whose turn is it, how many pieces does each side have, who can or cannot castle?
- the physical location of each player’s pieces on the board.
- and the third, builds a map of attacked and defended territory. Giraffe’s neural network gathers potential moves, mapping its options into branches to sort its “thinking.”
It is then capable of deciding which branches are most ‘interesting’ in any given position, and should be searched further, as well as which branches to discard. In human terms, this artificially intelligent system plays chess at FIDE International Master level, putting it among the top 2.2% of human chess players.
Placard for World’s Tallest Chess Piece. At 14 feet and 7 inches high, it is taller than a giraffe. If the piece had to be used on an actual board, the board would need to measure 72×72 feet, or roughly the size of two tennis courts! The board could serve as parking for 12 school buses.
Moreover, if you want to know how to teach yourself to be a chess master – check the free mini-course “Chess Training Plan for Rapid Improvement“. 🙂
Additionally, if you have chess engines and don’t know how to use them EFFECTIVELY, you can check our premium video “Chess engines: How to use them properly?”.