Partially supervised learning for pattern recognition

The investigation is conducted in the domain of bioinformatics and aims at the classification of DNA microarrays. The next paper, Semi-Supervised Linear Discriminant Analysis through Moment-Constraint Parameter Estimation by Marco Loog, introduces a variant of a semi-supervised linear discriminant function. The approach does not rely on arbitrary assumptions on the information mutually conveyed by labeled and unlabeled data that a diffusion graph based on Euclidean distance captures the proper relationships among the data. The meta-algorithm, which proceeds by finding prototypes from the labeled data and then clusters the remaining data iteratively, reduces the overall computational complexity of the procedure w.r.t. standard methods and may be instantiated with a variety of different kernel-based clustering techniques.