Characterization of Classication Algorithms
Download:
|
|
by J. Gama, P. Brazdil
http://www.liacc.up.pt/~jgama/mepia.ps.gz
Add To MetaCart
Abstract:
This paper is concerned with the problem of characterization of classication algorithms. The aim is to determine under what circumstances a particular classi cation algorithm is applicable. The method used involves generation of dierent kinds of models. These include regression and rule models, piecewise linear models (model trees) and instance based models. These are generated automatically on the basis of dataset characteristics and given test results. The lack of data is compensated for by various types of preprocessing. The models obtained are characterized by quantifying their predictive capability and the best models are identied. 1
Citations
| 545 | C4.5: Programs for – Quinlan - 1993 |
| 105 | Combining instance-based and model-based learning – Quinlan - 1993 |
| 10 | Decision Combination in Multiple Classi Systems – Ho, Hull, et al. - 1994 |
| 3 | Recursive automatic bias selection for classi construction – Brodley - 1995 |
| 2 | Instance-based learning algorithms". em – Aha, Kibler, et al. - 1991 |
| 2 | Goldstein M.(1984): Multivariate Analysis – Dillon |
| 2 | Gershenfeld N.A.(1993): Time Series Prediction, Forecasting the Future and Understanding the Past – Weigend |
| 1 | Henery R.(1994): \Characterizing the Applicability of Classi cation Algorithms using Meta Level Learning – Brazdil, Gama |
| 1 | Selecting a Classi Method by Cross- Validation – Shaer - 1993 |
| 1 | A Conservation Law for Generalization Performace – Shaer - 1994 |
