Random decision forests
Tin Kam Ho · Proceedings of the International Conference on Document Analysis and Recognition · 2002
Decision trees are attractive classifiers due to their high execution speed. But trees derived with traditional methods often cannot be grown to arbitrary complexity for possible loss of generalization accuracy on unseen data. The limitation on complexity usually means suboptimal accuracy on training data. Following the principles of stochastic modeling, we propose a method to construct tree-based classifiers whose capacity can be arbitrarily expanded for increases in accuracy for both training and unseen data. The essence of the method is to build multiple trees in randomly selected subspaces of the feature space. Trees in, different subspaces generalize their classification in complementary ways, and their combined classification can be monotonically improved. The validity of the method is demonstrated through experiments on the recognition of handwritten digits.
Cited by 5,054 works. doi:10.1109/icdar.1995.598994
Authors
References
- Classification and Regression Trees.
- Neural network ensembles
- Comparison of classifier methods: a case study in handwritten digit recognition
- Hierarchical Classifier Design Using Mutual Information
- Stochastic discrimination
- An overtraining-resistant stochastic modeling method for pattern recognition
- A Multifont Word Recognition System for Postal Address Reading
- An alternative method of stochastic discrimination with applications to pattern recognition
- A theory of multiple classifier systems and its application to visual word recognition
- Hierarchical mixtures of experts and the EM algorithm