A Harol

On euclidean correction for non-euclidean dissimilarities

Conference paper (2008) - Bob Duin (author), E.M. Pekalska (author), A Harol (author), W.J. Lee (author), H Bunke (author)

Pairwise feature evaluation for constructing reduced representations

Journal article (2007) - A Harol (author), C. Lai (author), E.M. Pekalska (author), Bob Duin (author)

Augmented embedding of dissimilarity data into (pseudo-)Euclidean spaces

Conference paper (2006) - A Harol (author), E.M. Pekalska (author), S Verzakov (author), Bob Duin (author)

Pairwiseproximitiesdescribethepropertiesofobjectsintermsoftheirsimilarities.Byusingdi¿erentdistance-basedfunctionsonemayencodedi¿erentcharacteristicsofagivenproblem.However,tousetheframeworkofstatisticalpatternrecognitionsomevectorrepresentationshouldbeconstructed.Oneofthesimples ...

Non-Euclidean or non-metric measures can be informative

Conference paper (2006) - E.M. Pekalska (author), A Harol (author), Bob Duin (author), B Spillmann (author), H Bunke (author)

StatisticallearningalgorithmsoftenrelyontheEuclideandistance.Inpractice,non-Euclideanornon-metricdissimilaritymeasuresmayarisewhencontours,spectraorshapesarecomparedbyeditdistancesorasaconsequenceofrobustobjectmatching[1,2].Itisanopenissuewhethersuchmeasuresareadvantageousforstat ...

On euclidean correction for non-euclidean dissimilarities

Pairwise feature evaluation for constructing reduced representations

Augmented embedding of dissimilarity data into (pseudo-)Euclidean spaces

Non-Euclidean or non-metric measures can be informative

Augmented embedding of dissimilarity data into (pseudo-) Euclidean spaces

A new model for prototype selection on distance data

Pairwise selection of features and prototypes