bsSVM

either the data or the labels corresponding to the features <code>x</code>.
It can be a <code>character</code> in which case the data is loaded using <code><a rd-options="" href="/link/liquidData?package=liquidSVM&version=1.2.2" data-mini-rdoc="liquidSVM::liquidData">liquidData</a></code>.
If it is of type <code>liquidData</code> then after <code>train</code>ing and <code>select</code>ion
the model is <code><a rd-options="" href="/link/test?package=liquidSVM&version=1.2.2" data-mini-rdoc="liquidSVM::test">test</a></code>ed using the testing data (<code>y$test</code>).

configuration parameters, see <a rd-options="" href="/link/Configuration?package=liquidSVM&version=1.2.2" data-mini-rdoc="liquidSVM::Configuration">Configuration</a>. Can be <code>threads=2, display=1, gpus=1,</code> etc.

the solver to use. Can be any of <code>KERNEL_RULE</code>, <code>SVM_LS_2D</code>,
<code>SVM_HINGE_2D</code>, <code>SVM_QUANTILE</code>, <code>SVM_EXPECTILE_2D</code>

solver

number of working sets to build and train

ws.number

how many samples to draw from the training set for each working set

ws.size

if <code>TRUE</code> also does the whole selection for this model

do.select

This routine performs bootstrap learning for all scenarios except multiclass classification.

Support vector machines (SVMs) and related kernel-based learning
algorithms are a well-known class of machine learning algorithms, for
non-parametric classification and regression.
liquidSVM is an implementation of SVMs whose key features are:
fully integrated hyper-parameter selection,
extreme speed on both small and large data sets,
full flexibility for experts, and
inclusion of a variety of different learning scenarios:
multi-class classification, ROC, and Neyman-Pearson learning, and
least-squares, quantile, and expectile regression.

Philipp Thomann

liquidSVM

A Fast and Versatile SVM Package

bsSVM function

either the data or the labels corresponding to the features <code>x</code>.
It can be a <code>character</code> in which case the data is loaded using <code><a rd-options='' href='liquidData'>liquidData</a></code>.
If it is of type <code>liquidData</code> then after <code>train</code>ing and <code>select</code>ion
the model is <code><a rd-options='' href='test'>test</a></code>ed using the testing data (<code>y$test</code>).

configuration parameters, see <a rd-options='' href='Configuration'>Configuration</a>. Can be <code>threads=2, display=1, gpus=1,</code> etc.

bsSVM: Bootstrap

Description

Usage

Arguments

Value