Machine teaches itself chess in 24 hours, attains international master level without being told the rules

Engine was built by a student, but used a ‘neural network’ to learn everything on its own

Sam Vallancey
Tuesday 15 September 2015 21:05 BST
Comments
The machine evaluated the pieces in play, and predicted which move of the millions of possibilities would be strong
The machine evaluated the pieces in play, and predicted which move of the millions of possibilities would be strong (Getty Images)

Your support helps us to tell the story

From reproductive rights to climate change to Big Tech, The Independent is on the ground when the story is developing. Whether it's investigating the financials of Elon Musk's pro-Trump PAC or producing our latest documentary, 'The A Word', which shines a light on the American women fighting for reproductive rights, we know how important it is to parse out the facts from the messaging.

At such a critical moment in US history, we need reporters on the ground. Your donation allows us to keep sending journalists to speak to both sides of the story.

The Independent is trusted by Americans across the entire political spectrum. And unlike many other quality news outlets, we choose not to lock Americans out of our reporting and analysis with paywalls. We believe quality journalism should be available to everyone, paid for by those who can afford it.

Your support makes all the difference.

A student has built a computer that managed to teach itself chess, and in just three days attained a level of skill comparable with some of the world’s most skilful players.

In the last two decades computers have become exponentially more powerful, but the “brute force” method of evaluating 200 million moves per second that Deep Blue employed was still the norm. Matthew Lai instead trained a “neural network” using example situations from real games of chess.

Rather than searching through all possible future moves and calculating the best one, Giraffe was programmed to learn the game in a similar way to humans, at a greatly accelerated rate.

Lai’s machine was built with a neural network which was fed 175 million examples of real games. It then evaluated the pieces in play and, contrary to traditional chess machines, predicted which move of the millions of possibilities would be strong and which would be weak.

Inspired by the human brain, the network’s nodes change as they are fed information, simulating the human process of learning by experience. Thanks to recent advances in computer speeds, these neural networks have grown in size and complexity, greatly increasing their power and proficiency.

Lai explained to Technology Review that “unlike most chess engines in existence today, Giraffe derives its playing strength not from being able to see very far ahead, but from being able to evaluate tricky positions accurately, and understanding complicated positional concepts that are intuitive to humans, but have been elusive to chess engines for a long time.”

Giraffe wasn’t built to become the best chess engine, but to demonstrate the potential power of computer learning. Neural networks like the one found in Giraffe are already outperforming humans in many areas of pattern recognition, with Google Deepmind matching game testers in classic Atari 2600 games.

Beyond playing games, Deep Learning Machines have a potential future in image recognition, drug discovery and even customer relations. As a potential step towards powerful artificial intelligence Facebook, Microsoft and Google have all invested in Deep Learning technologies in the past five years.

Join our commenting forum

Join thought-provoking conversations, follow other Independent readers and see their replies

Comments

Thank you for registering

Please refresh the page or navigate to another page on the site to be automatically logged inPlease refresh your browser to be logged in