Abstract
This paper surveys the context of feature extraction by neural network approaches, and compares and contrasts their behaviour as prospective data visualisation tools in a real world problem. We also introduce and discuss a hybrid approach which allows us to control the degree of discriminatory and topographic information in the extracted feature space.
| Original language | English |
|---|---|
| Title of host publication | Proceedings of International Conference on Artificial Neural Networks '95 |
| Place of Publication | Paris |
| Publisher | EC2 et Cie |
| Pages | 339-344 |
| Number of pages | 6 |
| Volume | 1 |
| ISBN (Print) | 2-910085-19-8 |
| Publication status | Published - 1995 |
| Event | Proceedings of ICANN '95 (Scientific Conference) - Paris, France Duration: 1 Jan 1995 → 1 Jan 1995 |
Conference
| Conference | Proceedings of ICANN '95 (Scientific Conference) |
|---|---|
| Country/Territory | France |
| City | Paris |
| Period | 1/01/95 → 1/01/95 |
Keywords
- neural network approaches
- data visualisation tools
- discriminatory and topographic information