predict.triTraining

Tri-training model built with the <code><a rd-options="" href="/link/triTraining?package=ssc&version=2.1-0" data-mini-rdoc="ssc::triTraining">triTraining</a></code> function.

object

A object that can be coerced as matrix.
Depending on how was the model built, <code>x</code> is interpreted as a matrix 
with the distances between the unseen instances and the selected training instances, 
or a matrix of instances.

This parameter is included for compatibility reasons.

Predicts the label of instances according to the <code>triTraining</code> model.

Provides a collection of self-labeled techniques for semi-supervised
classification. In semi-supervised classification, both labeled and unlabeled
data are used to train a classifier. This learning paradigm has obtained promising
results, specifically in the presence of a reduced set of labeled examples.
This package implements a collection of self-labeled techniques to construct a
classification model. This family of techniques enlarges the original labeled set
using the most confident predictions to classify unlabeled data. The techniques
implemented can be applied to classification problems in several domains by the
specification of a supervised base classifier. At low ratios of labeled data, it
can be shown to perform better than classical supervised classifiers.

Christoph Bergmeir

Semi-Supervised Classification Methods

Mabel Gonz<c3><a1>lez

Osmani Rosado-Falc<c3><b3>n

Jos<c3><a9> Daniel Rodr<c3><ad>guez

Isaac Triguero

Jos<c3><a9> Manuel Ben<c3><ad>tez

predict.triTraining function

Tri-training model built with the <code><a rd-options='' href='triTraining'>triTraining</a></code> function.

predict.triTraining: Predictions of the Tri-training method

Description

Usage

Arguments

Value

Details