Intended learning outcomes *
The course studies fundamentals of data mining, data stream processing, and machine learning algorithms for analyzing very large amounts of data. We will use big data processing platforms, such as MapReduce, Spark and Apache Flink, for implementing parallel algorithms, as well as computation systems for data stream processing, such as Storm and InfoSphere.
After this course, students will be able to mine different types of data, e.g., high-dimensional data, graph data, and infinite/never-ending data (data streams); as well as to program and build data-mining applications. They are also expected to know how to solve problems in real-world applications, e.g., recommender systems, association rules, link analysis, and duplicate detection. Moreover, they will master various mathematical techniques, e.g., linear algebra, optimization, and dynamic programming.