Learn R Programming
⚠️There's a newer version (0.3-24) of this package.Take me there.

bst (version 0.3-2)

Gradient Boosting

Description

The package contains HingeBoost for binary and multi-class classification, with unequal misclassification costs for binary case. Functional gradient descent algorithm to optimize the hinge loss. The algorithm can fit linear and nonlinear classifiers.

Copy Link

Version

Install

install.packages('bst')

Monthly Downloads

1,249

Version

0.3-2

License

GPL-2

Maintainer

Zhu Wang

Last Published

January 17th, 2012

Functions in bst (0.3-2)

bst-package

Boosting for Classification and Regression
bst_control

Control Parameters for Boosting
loss

Internal Function
cv.mada

Cross-Validation for one-vs-all AdaBoost with multi-class problem
cv.msvm

Cross-Validation
msvm

Boosting for Multi-class Classification
bst

Boosting for Classification and Regression
mhinge

Multi-class HingeBoost
ex1data

Generating Three-class Data
cv.bst

Cross-Validation for Binary HingeBoost
mada

Multi-class AdaBoost
cv.mhinge

Cross-Validation for one-vs-all HingeBoost with multi-class problem