709 research outputs found
Median fuzzy-c-means for clustering dissimilarity data
No full textGeweniger T, Zülke D, Hammer B, Villmann T. Median fuzzy-c-means for clustering dissimilarity data. Neurocomputing. 2010;73(7-9):1109-1116
Median variant of fuzzy-c-means
No full textGeweniger T, Zühlke D, Hammer B, Villmann T. Median variant of fuzzy-c-means. In: Verleysen M, ed. European Symposium on Artificial Neural Networks. Evere: d-side publications; 2009: 523-528
Fuzzy variant of affinity propagation in comparison to median fuzzy c-means
No full textGeweniger T, Zühlke D, Hammer B, Villmann T. Fuzzy variant of affinity propagation in comparison to median fuzzy c-means. In: Principe JC, Miikkulainen R, eds. Advances in Self-Organizing Maps. 2009: 72-79
Fuzzy Labeled Self-Organizing Map with Label-Adjusted Prototypes
No full textVillmann T, Seiffert U, Schleif F-M, Brüß C, Geweniger T, Hammer B. Fuzzy Labeled Self-Organizing Map with Label-Adjusted Prototypes. In: Schwenker F, ed. Proceedings of Conference Artificial Neural Networks in Pattern Recognition. Berlin: Springer; 2006: 46-56
Fuzzy variants of prototype based clustering and classification algorithms
No full textGroeperen en classificeren op basis van prototypen is een specifiek onderwerp binnen de gebieden van het machinale leren en kunstmatige neurale netwerken. Het kan toegepast worden voor data mining, statistische data-analyse, patroonherkenning en informatiewinning.
Datapunten, die in werkelijkheid tot verschillende groepen of klassen behoren, kunnen overlappen waardoor ze niet eenduidig gescheiden kunnen worden. Het overlappen van data wordt fuzziness genoemd, en verwijst naar de probabilistische of possibilistische toekenningen van datapunten aan groepen of klassen. Het kan gezien worden als leren met onzekerheden. In dit proefschrift worden een aantal gecontroleerde en ongecontroleerd methoden - specifiek c-Means, Learning Vector Quantization, Self Organizing Maps, Neural Gas and Affinity Propagation - uitgebreid om om te kunnen gaan met dit soort fuzziness. Hoewel een aantal van de genoemde methoden al varianten heeft die om kunnen gaan met fuzzy data, betreffen de voorgestelde aanpassingen verschillende verdere aspecten, zoals het groeperen van median data, het gebruik van divergenties als nabijheidsmaten en relevance learning. Daarnaast worden verschillende maten gebruikt om fuzzy classificatie en fuzzy groeperen te evalueren.
Prototype based clustering and classification is a specific topic in the field of machine learning and artificial neural networks. Unsupervised clustering refers to grouping of data into sets of similar objects represented by prototypes and is among others applicable for explorative data mining, statistical data analysis, pattern recognition, and information retrieval. Supervised classification determines prototypes representing respective classes by taking a priori known class information into account. After successful prototype positioning new data samples can be classified accordingly. In practical applications data, which in fact belongs to different groups, i. e. clusters or classes, might be overlapping and therefore cannot be separated clearly. This overlapping of data is called fuzziness and refers to probabilistic or possibilistic assignments of data points to clusters or classes and has to be distinguished from fuzzy sets or fuzzy logic. Rather, it is learning with uncertainties. In this thesis some supervised and unsupervised methods -- in particular c- Means, Learning Vector Quantization, Self Organizing Maps, Neural Gas, and Affinity Propagation -- are modified or extended to incorporate this kind of fuzziness. Although some of the mentioned methods already have variants dealing with fuzzy data, the now proposed modifications concern different further aspects like clustering median data, using divergences as dissimilarity measure, or learning relevances. Further, to evaluate a fuzzy classification or cluster solution different measures are used. One of them, the Fleiss‘ Kappa Index is modified to be also applicable to fuzzy solutions.
Median fuzzy c-means for clustering dissimilarity data
No full textS.1109-1116Median clustering is a powerful methodology for prototype based clustering of similarity/dissimilarity data. In this contribution we combine the median c-means algorithm with the fuzzy c-means approach, which is only applicable for vectorial (metric) data in its original variant. For the resulted median fuzzy c-means approach we prove convergence and investigate the behavior of the algorithm in several experiments including real world data from psychotherapy research.73Nr.7-
- …
