Package weka.classifiers.mi

Class Summary
CitationKNN Modified version of the Citation kNN multi instance classifier.

For more information see:

Jun Wang, Zucker, Jean-Daniel: Solving Multiple-Instance Problem: A Lazy Learning Approach.
MDD Modified Diverse Density algorithm, with collective assumption.

More information about DD:

Oded Maron (1998).
MIBoost MI AdaBoost method, considers the geometric mean of posterior of instances inside a bag (arithmatic mean of log-posterior) and the expectation for a bag is taken inside the loss function.

For more information about Adaboost, see:

Yoav Freund, Robert E.
MIDD Re-implement the Diverse Density algorithm, changes the testing procedure.

Oded Maron (1998).
MIEMDD EMDD model builds heavily upon Dietterich's Diverse Density (DD) algorithm.
It is a general framework for MI learning of converting the MI problem to a single-instance setting using EM.
MILR Uses either standard or collective multi-instance assumption, but within linear regression.
MINND Multiple-Instance Nearest Neighbour with Distribution learner.

It uses gradient descent to find the weight for each dimension of each exeamplar from the starting point of 1.0.
MIOptimalBall This classifier tries to find a suitable ball in the multiple-instance space, with a certain data point in the instance space as a ball center.
MISMO Implements John Platt's sequential minimal optimization algorithm for training a support vector classifier.

This implementation globally replaces all missing values and transforms nominal attributes into binary ones.
MISVM Implements Stuart Andrews' mi_SVM (Maximum pattern Margin Formulation of MIL).
MIWrapper A simple Wrapper method for applying standard propositional learners to multi-instance data.

For more information see:

E.
SimpleMI Reduces MI data into mono-instance data.
TLD Two-Level Distribution approach, changes the starting value of the searching algorithm, supplement the cut-off modification and check missing values.

For more information see:

Xin Xu (2003).
TLDSimple A simpler version of TLD, mu random but sigma^2 fixed and estimated via data.

For more information see:

Xin Xu (2003).