Name
Title | ||
|---|---|---|
Polytope ARTMAP: Pattern Classification Without Vigilance Based on General Geometry Categories |
Abstract | ||
|---|---|---|
This paper proposes polytope ARTMAP (PTAM), an adaptive resonance theory (ART) network for classification tasks which does not use the vigilance parameter. This feature is due to the geometry of categories in PTAM, which are irregular polytopes whose borders approximate the borders among the output predictions. During training, the categories expand only towards the input pattern without category overlap. The category expansion in PTAM is naturally limited by the other categories, and not by the category size, so the vigilance is not necessary. PTAM works in a fully automatic way for pattern classification tasks, without any parameter tuning, so it is easier to employ for nonexpert users than other classifiers. PTAM achieves lower error than the leading ART networks on a complete collection of benchmark data sets, except for noisy data, without any parameter optimization. |
Year | DOI | Venue |
|---|---|---|
2007 | 10.1109/TNN.2007.894036 | IEEE Transactions on Neural Networks |
Keywords | Field | DocType |
ART neural nets,geometry,pattern classification,adaptive resonance theory,category size,geometry,noisy data,parameter tuning,pattern classification,polytope ARTMAP,Adaptive resonance theory (ART) neural networks,general geometry categories,parameter tuning,polytope category representation regions (CRRs),vigilance | Noisy data,Data set,Computer science,Polytope,Artificial intelligence,Geometry,Artificial neural network,Adaptive resonance theory,Pattern recognition,Adaptive system,Signal-to-noise ratio,Vigilance (psychology),Machine learning | Journal |
Volume | Issue | ISSN |
18 | 5 | 1045-9227 |
Citations | PageRank | References |
11 | 0.66 | 26 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Dinani Gomes Amorim | 1 | 11 | 0.66 |
| Manuel Fernandez-Delgado | 2 | 19 | 1.47 |
| Senén Barro Ameneiro | 3 | 11 | 0.66 |