188 search results - page 1 / 38 » Ensemble Selection Using Diversity Networks |
DMIN
2006
13 years 6 months ago
2006
- An ideal ensemble is composed of base classifiers that perform well and that have minimal overlap in their errors. Eliminating classifiers from an ensemble based on a criterion t...
SBRN
2006
IEEE
13 years 10 months ago
2006
IEEE
CIDM
2009
IEEE
13 years 11 months ago
2009
IEEE
— Both theory and a wealth of empirical studies have established that ensembles are more accurate than single predictive models. Unfortunately, the problem of how to maximize ens...
INFFUS
2006
13 years 4 months ago
2006
Adjusted Rand index is used to measure diversity in cluster ensembles and a diversity measure is subsequently proposed. Although the measure was found to be related to the quality...
PRL
2010
13 years 3 months ago
2010
The nearest-neighbour (1NN) classifier has long been used in pattern recognition, exploratory data analysis, and data mining problems. A vital consideration in obtaining good res...