Comparative study of select non parametric and ensemble machine learning classification techniques
Authors:
- 18 December 2020
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 110-115
Abstract
Supervised classification is a machine learning approach where data is classified among various discrete classes which could be binary or multi-class. Decision Tree, random Forest, Rotation Forest, AdaBoost, Extra Tree, XGBoost are some of the ensembles that classify data on trained model under certain criterion. AUROC and in-sample out-sample error is used as performance measure of algorithms on benchmark datasets. Hyperparameter tuning is done to improve performance and avoid overfitting.Keywords
This publication has 13 references indexed in Scilit:
- XGBoost2016
- Explaining AdaBoost2013
- Ensemble Decision Tree Classifier For Breast Cancer DataInternational Journal of Information Technology Convergence and Services, 2012
- Decision trees: a recent overviewArtificial Intelligence Review, 2011
- Rotation Forest: A New Classifier Ensemble MethodIEEE Transactions on Pattern Analysis and Machine Intelligence, 2006
- Decision Trees2006
- Extremely randomized treesMachine Learning, 2006
- Machine learning from examples: Inductive and Lazy methodsData & Knowledge Engineering, 1998
- A review of machine learningThe Knowledge Engineering Review, 1997
- Measuring the VC-Dimension of a Learning MachineNeural Computation, 1994