An Artificial Neural Network That Uses Coarse Allocentric Coding of Direction to Represent Distances Between Locations in a Metric Space

@article{Dawson2005AnAN,
  title={An Artificial Neural Network That Uses Coarse Allocentric Coding of Direction to Represent Distances Between Locations in a Metric Space},
  author={Michael R. W. Dawson and Patricia M. Boechler and Jill Orsten},
  journal={Spatial Cognition & Computation},
  year={2005},
  volume={5},
  pages={29-67}
}
An artificial neural network was trained to rate the distances between all possible pairs taken from a set of thirteen different cities on the map of Alberta. After learning to solve this problem, the internal structure of the network was analyzed. It was found that in spite of the fact that the network was trained to rate distances, the hidden units in the… CONTINUE READING