An artificial intelligence machine called Giraffe that has taught itself to play chess by evaluating positions much more like humans and in an entirely different way to conventional chess engines may well be the future of AI, according
to a recent report in the MIT Technology Review. “Straight out of the box, the new machine plays at the same level as the best conventional chess engines, many of which have been fine-tuned over many years,” the report says. The technology behind the new machine — developed by Matthew Lai (left) at Imperial College London –is a neural network that consists of several layers of nodes that are connected in a way that change as the system is trained. “Lai says it should be straightforward to apply the same approach to other games,” the report concludes. “One that stands out is the traditional Chinese game of Go, where humans still hold an impressive advantage over their silicon competitors. Perhaps Lai could have a crack at that next.”
Thanks to Fred D. Baldwin for passing this along.
American Go E-Journal
Can Giraffe Crack Go?
Sunday September 27, 2015