Abstract
Localist models of, for example, the classification of multidimensional stimuli, can run into problems if generalization is attempted when many of the stimulus dimensions are irrelevant to the classification task in hand. A procedure is suggested by representations that focus on the relevant dimensions only. These permit good generalization which would be lacking in a simple exemplar-based model.
| Original language | English |
|---|---|
| Title of host publication | Connectionist models of learning, development and evolution |
| Subtitle of host publication | Proceedings of the 6th Neural Computation and Psychology Workshop |
| Editors | Robert M French, Jacques P Sougne |
| Publisher | Springer Nature Link |
| Pages | 105-112 |
| Number of pages | 8 |
| ISBN (Print) | 1852333545, 9781852333546 |
| Publication status | Published - 2001 |
| Event | 6th Neural Computation and Psychology Workshop - Liege, Belgium Duration: 16 Sept 2000 → 18 Sept 2000 |
Workshop
| Workshop | 6th Neural Computation and Psychology Workshop |
|---|---|
| Country/Territory | Belgium |
| City | Liege |
| Period | 16/09/00 → 18/09/00 |