A parallel network that learns to play backgammon
Artificial Intelligence
Review of neural networks for speech recognition
Neural Computation
Connectionist learning of expert preferences by comparison training
Advances in neural information processing systems 1
Backpropagation applied to handwritten zip code recognition
Neural Computation
Hi-index | 0.00 |
Neurogammon 1.0 is a backgammon program which uses multilayer neural networks to make move decisions and doubling decisions. The networks learned to play backgammon by backpropagation training on expert data sets. At the recently held First Computer Olympiad in London, Neurogammon won the backgammon competition with a perfect record of five wins and no losses, thereby becoming the first learning program ever to win a tournament.