Machine learning and data mining 1 [ KMI/MLDM1 ]

The course is the first part of the two semester course devoted to principles and main methods of data mining and machine learning. After problem introduction with defining these notions and looking at data and their preprocessing the basic data minig methods of classification, association analysis and clustering used (not only) in machine learning are discussed, from the algorithmic point of view.

Lectures

Intro: Data mining: extracting information from data, KDD, typical tasks. Machine learning: learning from information from data, phases and types.
Data: Types of data and attributes, quality a preprocessing (sampling, normalization, discretization), similarity and dissimimlarity of objects, summary statistics a visualization.
Classification: Decision trees, overfitting problem, evaluation of performance, rule-based, nearest neighbor, naive Bayes, support vector machines (SVM), regression.
Association analysis: Itemsets, rules, Apriori algorithm, interestingness evaluation.
Cluster analysis: types of clusters, K-means, hierarchical, density-based, expectation-maximization (EM), quality evaluation.

Literature

Tan P.-N., Steinbach M., Kumar V.: Introduction to Data Mining. Pearson Education, 2005.
Marsland S.: Machine Learning: An Algorithmic Perspective, 2nd ed. Chapman and Hall/CRC, 2014.
Zaki M. J., Meira W. Jr: Data Mining and Analysis: Fundamental Concepts and Algorithms. Cambridge University Press, 2014.
Poole D. L., Mackworth A. K.: Artificial Intelligence: Foundations of Computational Agents, 2nd ed. Cambridge University Press, 2017.