See: Description
Interface | Description |
---|---|
DissimilarityClassifier |
This is an interface for dissimilarity based classifiers, that is:
Classifiers that are able to provide an estimate of the most likely class
label for some given, unseen data point based on their dissimilarities to
some set of training data points for which the true label is known.
|
DistanceIndex.IndexFilter |
This is an interface for functions that filter indices.
|
Class | Description |
---|---|
AbstractDissimilarityClassifier |
This is a convenience extension of the DissimilarityClassifier interface,
which already implements most of the functionality to make the implementation
of DissimilarityClassifiers easier.
|
DistanceIndex | |
DistanceIndex.AndFilter |
Returns true if and only if both underlying filters return true.
|
DistanceIndex.IdentityFilter |
This filter returns true if the input index is equal to the reference
index.
|
DistanceIndex.Labelfilter |
Returns true if and only if the label of the input data point is the same
as the reference label.
|
DistanceIndex.NotFilter |
Returns true if and only if the underlying filter returns false.
|
KNNClassifier |
This implements a very basic k-nearest neighbor classifier: Given a set of
data points and a (trained) AlignmentAlgorithm it can determine the k next
datapoints for a given new datapoint and calculate the label for it based on
the majority of votes.
|
LMNNClassifier |
This implements a Large Margin Nearest Neighbor classifier as suggested by
Weinberger, Saul et al.
|
LMNNGradientCalculator<X> |
This implements the Large Margin Nearest Neighbor Metric Learning approach
by Weinberger et al.
|
Copyright (C) 2016-2018 Benjamin Paaßen, AG Theoretical Computer Science, Centre of Excellence Cognitive Interaction Technology (CITEC), University of Bielefeld, licensed under the AGPL v. 3: http://openresearch.cit-ec.de/projects/tcs . This documentation is licensed under the conditions of CC-BY-SA 4.0: https://creativecommons.org/licenses/by-sa/4.0/