Name
Abstract | ||
|---|---|---|
We have previously investigated the use of artificial neural networks to ride simulated motorbikes in a new com- puter game. These artificial neural networks were trained using two different training techniques, the Evolutionary Algorithms and the Backpropagation Algorithm. In this paper, we detail some of the investigations to improve the training, with a view to having the computer controlled bikes performing as well or better than a human player at playing the game. Techniques investigated here to improve backpropagation are bagging and boosting, while alternative crossover techniques have also been investigated to improve Evolution. |
Year | DOI | Venue |
|---|---|---|
2006 | 10.1109/CIG.2006.311698 | CIG |
Keywords | Field | DocType |
ar- tificial neural networks,computational intelligence,motorbikes,back propagation,driving game.,genetic algorithm,evolutionary algorithm,computer simulation,artificial intelligence,neural network,evolutionary computation,backpropagation,neural nets,artificial neural networks,computer networks,backpropagation algorithm,computational modeling,artificial intelligent,artificial neural network | Crossover,Evolutionary algorithm,Computational intelligence,Simulation,Computer science,Evolutionary computation,Artificial intelligence,Boosting (machine learning),Artificial neural network,Backpropagation,Genetic algorithm,Machine learning | Conference |
Citations | PageRank | References |
20 | 2.29 | 1 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Benoit Chaperot | 1 | 21 | 2.69 |
| Colin Fyfe | 2 | 508 | 55.62 |