Survey
* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project
* Your assessment is very important for improving the work of artificial intelligence, which forms the content of this project
4IZ451 – Knowledge Discovery in Databases English Knowledge Discovery in Databases Czech Dobývání znalostí z databází ECTS credits 6 Type of course 2/2 Lecturer Prof. Ing. Petr Berka, CSc. Prerequisities Not 4IZ435 Aims of the course Knowledge Discovery in Databases (KDD) can be defined as "Non-trivial process of identifying valid, novel, potentially useful and ultimately understandable patterns from data". This modern branch of computer science is on the edge of database technologies, statistics and artificial intelligence. KDD techniques can be used to solve classification, prediction, summarization or segmentation tasks on various application areas. Learning outcomes and competences Students will get familiar with the methods used for knowledge discovery in databases from both theoretical and practical point of view. The main focus of the lectures will be on description of used data mining methods and algorithms. In practical part, the students will work with selected data mining systems. Upon successful completion of this course, students will be able to: - understand the role of KDD for data analysis, - understand the basic principles of various data mining algorithms, - understand the basic methods of evaluation of created models, - understand basic preprocessing operations, - formulate and solve KDD tasks for real-world data, - use the systems Weka, PASW Modeler and SAS Enterprise Miner. Course contents - The process of KDD: tasks, steps, methodologies - The background for KDD: databases, statistics, machine learning - Machine learning methods: decision trees, decision rules, association rules, neural nets, bayesian methods, genetic algorithms, instance based learning - Evaluation what has been learned - Data preprocessing methods - New trends: text mining, web mining Teaching methods and workload Type of teaching method Daily attendance Distance form Participation in lectures 26 h 6h Attendance at seminars/workshops/tutorials 26 h 0h Preparation for seminars/workshops/tutorials 26 h 45 h Preparation of term paper 39 h 52 h Preparation of presentation 0h 13 h Preparation for final test 39 h 40 h Total 156 h 156 h Assessment methods Requirement type Daily attendance Distance form Term paper 30 % 30 % Presentation 0% 10 % Final test 70 % 60 % Total 100 % 100 % Recommended readings ISBN Title Authors Year 0120884070 Data Mining: Practical Machine Learning Tools and Techniques, Second Edition Witten,I. - Frank,E. 2005 Han, J. - Kamber, M. 2001 1-55860-489-8 Data mining concepts and techniques