Neurogammon is a computer

Computer

A computer is a programmable machine designed to sequentially and automatically carry out a sequence of arithmetic or logical operations. The particular sequence of operations can be changed readily, allowing the computer to solve more than one kind of problem...

 backgammon

Backgammon

Backgammon is one of the oldest board games for two players. The playing pieces are moved according to the roll of dice, and players win by removing all of their pieces from the board. There are many variants of backgammon, most of which share common traits...

 program written by Gerald Tesauro at IBM

IBM

International Business Machines Corporation or IBM is an American multinational technology and consulting corporation headquartered in Armonk, New York, United States. IBM manufactures and sells computer hardware and software, and it offers infrastructure, hosting and consulting services in areas...

's Thomas J. Watson Research Center

Thomas J. Watson Research Center

The Thomas J. Watson Research Center is the headquarters for the IBM Research Division.The center is on three sites, with the main laboratory in Yorktown Heights, New York, 38 miles north of New York City, a building in Hawthorne, New York, and offices in Cambridge, Massachusetts.- Overview :The...

. It was the first viable computer backgammon program implemented as a neural net

Artificial neural network

An artificial neural network , usually called neural network , is a mathematical model or computational model that is inspired by the structure and/or functional aspects of biological neural networks. A neural network consists of an interconnected group of artificial neurons, and it processes...

, and set a new standard in computer backgammon play. It won the 1st Computer Olympiad

1st Computer Olympiad

The 1st Computer Olympiad took place at the Park Lane Hotel in London, UK from 9 August 1989 to 15 August 1989. In this Computer Olympiad, computer programs competed against each other at a variety of games, including Awari, Backgammon, Bridge, Checkers, Chess, Chinese Chess, Connect-Four,...

 in London in 1989, handily defeating all opponents. Its level of play was that of an intermediate-level human player.

Neurogammon contains seven separate neural networks, each with a single hidden layer. One network makes doubling-cube decisions; the other six choose moves at different stages of the game. The networks were trained by backpropagation

Backpropagation

Backpropagation is a common method of teaching artificial neural networks how to perform a given task. Arthur E. Bryson and Yu-Chi Ho described it as a multi-stage dynamic system optimization method in 1969 . It wasn't until 1974 and later, when applied in the context of neural networks and...

 from transcripts of 400 games in which the author played himself. The author's move was taught as the best move in each position.

In 1992, Tesauro completed TD-Gammon

TD-Gammon

TD-Gammon was a computer backgammon program developed in 1992 by Gerald Tesauro at IBM's Thomas J. Watson Research Center. Its name comes from the fact that it is an artificial neural net trained by a form of temporal-difference learning, specifically TD-lambda....

, which combined a form of unsupervised learning

Unsupervised learning

In machine learning, unsupervised learning refers to the problem of trying to find hidden structure in unlabeled data. Since the examples given to the learner are unlabeled, there is no error or reward signal to evaluate a potential solution...

with the human-designed input features of Neurogammon, and played at the level of a world-class human tournament player.