An AI researcher at Imperial College in London has built a deep-learning machine called 'Giraffe' that plays chess like humans do and not like an engine. Matthew Lai used a neural network that can be trained using examples. He fed it a huge database of 175 million positions from actual games and instructed the computer to look at the number and type of pieces in play, the locations of the pieces, and the places they could move. Nothing new there, but unlike a normal engine which would then would then evaluate each position and then select the move with the best evaluation number, Lai's program then learns to predict what moves were likely to be strong and weak.
After 72 hours of the learning process, Giraffe managed to attain the same level of play as the best engines. It can predict the best move 46 percent of the time and the best move is in its top three selections 70 percent of the time.
In a Technology Review Lai was quoted as saying, "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. This is especially important in the opening and endgame phases where it plays exceptionally well."
Lai has published the details of his machine-learning algorithm HERE. Also, see the article in the MIT Technology Review.