Package | Description |
---|---|
de.citec.tcs.alignment.learning |
This module is a custom implementation of the Large Margin
Nearest Neighbor classification scheme of Weinberger, Saul, et al.
|
Modifier and Type | Method and Description |
---|---|
static TreeSet<DistanceIndex> |
DistanceIndex.getImposters(int j,
double[] distances,
int[] labels,
double margin)
Returns the indices of all data points from other classes, that are
closer to the reference data point than the target neighbor
with index j (including a margin of safety).
|
static TreeSet<DistanceIndex> |
DistanceIndex.getKNearest(int K,
double[] distances,
DistanceIndex.IndexFilter filter)
Returns the indices of the K data points with the lowest distance that
meet some filter criterion.
|
static TreeSet<DistanceIndex> |
DistanceIndex.getKNearest(int K,
int i,
double[] distances)
Returns the indices of the K nearest neighbors of the reference data
point sorted in ascending order with respect to their distance.
|
static TreeSet<DistanceIndex> |
DistanceIndex.getPointsInRadius(double radius,
double[] distances,
DistanceIndex.IndexFilter filter)
Returns the indices of all data points, which have a lower distance than
the given radius and meet some additional filter criterion.
|
static TreeSet<DistanceIndex> |
DistanceIndex.getTargetNeighborsTest(int K,
int label,
double[] distances,
int[] labels)
Returns the indices of the K nearest neighbors of the reference data
point that are from the same class as the reference data point.
|
static TreeSet<DistanceIndex> |
DistanceIndex.getTargetNeighborsTraining(int K,
int i,
double[] distances,
int[] labels)
Returns the indices of the K nearest neighbors of the reference data
point that are from the same class as the reference data point.
|
static TreeSet<DistanceIndex> |
DistanceIndex.getTargetNeighborsTraining(int K,
int i,
int label,
double[] distances,
int[] labels)
Returns the indices of the K nearest neighbors of the reference data
point that are from the same class as the reference data point.
|
Modifier and Type | Method and Description |
---|---|
int |
DistanceIndex.compareTo(DistanceIndex o) |
Modifier and Type | Method and Description |
---|---|
double |
LMNNClassifier.calculateLMNNCostFunction(TreeSet<DistanceIndex> targetNeighbors,
double[] distances)
Calculates the LMNN cost function given the target neighbors of some data
point and its distances to the training data points.
|
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/