Advanced methods for prototype-based classification
PhD ceremony: Ms. P. Schneider, 14.45 uur, Academiegebouw, Broerstraat 5, Groningen
Thesis: Advanced methods for prototype-based classification
Promotor(s): prof. M. Biehl, prof. N. Petkov
Faculty: Mathematics and Natural Sciences
The thesis presents research on Learning Vector Quantization (LVQ). LVQ is a simple and intuitive classification technique: LVQ algorithms learn prototypical vectors for the classes of the considered data set. The prototypes are used for a distance-based classification, i.e. a patter is assigned to the class represented by the closest prototype with respect to a certain distance measure.
The thesis deals with two issues: a new approach for metric adaptation in LVQ is presented and modifications of one specific learning algorithm, namely Robust Soft LVQ, are introduced.
Metric adaptation techniques allow to learn problem specific distance measures from the training data. Since the classifier's decision depends on distances between prototypes and feature vectors, the selected metric is a key issue for the performance of LVQ. We extend the Euclidean distance by a matrix of adaptive weight values. The diagonal entries of the matrix quantify the importance of single features for classification while off-diagonal elements correspond to the relevance of pairs in the classification scheme. Practical applications show that the advanced metric allows to improve the classification of the employed algorithms significantly. Furthermore, the metric parameters provide insight into the nature of the data. The convergence behaviour of the training algorithms is also analysed theoretically.
The proposed modifications of Robust Soft LVQ concern the treatment of the algorithm's hyperparameter, the decision rule for classification, and we present a generalization of the algorithm with respect to vectorial class labels of the input data. The methods are illustrated by means of practical experiments.
Last modified: | 13 March 2020 01.13 a.m. |
More news
-
01 April 2025
NSC’s electoral reform plan may have unwanted consequences
The new voting system, proposed by minister Uitermark, could jeopardize the fundamental principle of proportional representation, says Davide Grossi, Professor of Collective Decision Making and Computation at the University of Groningen
-
01 April 2025
‘AiNed’ National Growth Fund grant for speeding adoption of AI at SMEs
Professor Ming Cao receives an ‘AiNed’ Growth Fund grant of EUR 2.4 million for research that will contribute to faster adoption of AI at SMEs in the technical industry in the Netherlands.
-
01 April 2025
'Diversity leads to better science'
In addition to her biological research on ageing, Hannah Dugdale also studies disparities relating to diversity in science. Thanks to the latter, she is one of the two 2024 laureates of the Athena Award, an NWO prize for successful and inspiring...