Package gov.sandia.cognition.learning.function.distance

Provides distance functions.


Interface Summary
DivergenceFunctionContainer<FirstType,SecondType> Interface for a class that holds a divergence function.

Class Summary
ChebyshevDistanceMetric An implementation of the Chebyshev distance, which is the absolute value of the largest difference between two vectors in a single dimension.
CosineDistanceMetric The CosineDistanceMetric class implements a semimetric between two vectors based on the cosine between the vectors.
DefaultDivergenceFunctionContainer<FirstType,SecondType> The DefaultDivergenceFunctionContainer class implements an object that holds a divergence function.
DivergencesEvaluator<InputType,ValueType> Evaluates the divergence (distance) between an input and a list of values, storing the resulting divergence values in a vector.
DivergencesEvaluator.Learner<DataType,InputType,ValueType> A learner adapter for the DivergencesEvaluator.
EuclideanDistanceMetric The EuclideanDistanceMetric implements a distance metric that computes the Euclidean distance between two points.
EuclideanDistanceSquaredMetric The EuclideanDistanceSquaredMetric implements a distance metric that computes the squared Euclidean distance between two points.
IdentityDistanceMetric A distance metric that is 0 if two objects are equal and 1 if they are not.
ManhattanDistanceMetric The ManhattanDistanceMetric class implements a distance metric between two vectors that is implemented as the sum of the absolute value of the difference between the elements in the vectors.
MinkowskiDistanceMetric An implementation of the Minkowski distance metric.
WeightedEuclideanDistanceMetric A distance metric that weights each dimension of a vector differently before computing Euclidean distance.

Package gov.sandia.cognition.learning.function.distance Description

Provides distance functions. Distance functions are useful for learning algorithms such as clustering for determining the distance between two objects.

Justin Basilico