Parameter estimation methods (EM algorithm, mixture models), feature extraction methods (PCA, PLSR, etc.), data classification methods (hierarchical, k-means, SOM, etc.). Νeural networks (supervised / unsupervised), Bayesian networks, graphical models. Parallel processing for machine learning. Machine learning applications in Computational Biology: decoding DNA sequences, identification of mutations (SNPs), data analysis and categorization of gene expression profiles (microarrays), data processing and classification of proteomics and metabolomics data (2D gels, LC-MS, Seldi –MS spectra). Gene and protein interaction networks, extraction of biological system models from multidimensional heterogeneous bioinformatics data. Models comparison methods, multidimensional data visualization, applications to systems biology. Developing algorithms and software for practical problem solving using real data.