Obligatory course for Computer Science and Information Systems and Data Science programs. Delivered in Polish as Bazy Danych and in English. During the lectures we discuss inter alia relational databases, data modeling, transactional processing, introduction to data warehouses and geodatabases, but also advanced mechanisms of database management systems, such as performance tuning, managing backups and permissions. During the laboratories students learn how to develop logical and physical data models, use SQL to query, update and manage data and data models, develop stored procedures, develop client applications interacting with database management systems and work on transactional processing including transaction isolation.
More ...The objective of this obligatory course of BSc in Data Science program (English name: Data Storage in Big Data Systems) course is to provide students with in-depth knowledge of key platforms used to collect, transform, and store large volumes of data in rest and data in motion. Platforms covered include platforms used for data collection, transformation and ingestion (Apache NiFi), data storage (Apache Hadoop, NoSQL platforms such as Apache Cassandra), event streaming platforms (Apache Kafka), processing frameworks (Apache Spark) and other. Students develop projects combining these platforms for data collection and analysis.
More ...The objective of this obligatory course of the MSc in Data Science program is to provide students with in-depth knowledge of data analytics for large volumes of data, including both batch and stream processing. We discuss both technical aspects such as different approaches to data stream processing (batch-based, microbatches and continuous), machine learning for Big Data, and nontechnical aspects such as ethical aspects of (Big) data analytics.
More ...The aim of this elective course is to provide all interested students of especially Computer Science programs with knowledge about the architecture and sample Big Data platforms used to collect and store arbitrary large data, as well as the practical skills needed to acquire, transform and store data in these environments. Prerequisites: Knowledge of databases including SQL language (acquired prior to or in parallel to the course), knowledge of UNIX/Linux operating system, programming skills in at least Python or Java.
More ...This elective course delivered in Polish (English name: Data Analytics: Key Methods and Systems) complements courses on machine learning offered by the university by providing in-depth discussion of the whole data mining process, starting from data acquisition, through preliminary data analysis, data reduction techniques (feature and instance selection, introduction to dimensionality reduction) to evaluation of machine learning models, including both performance measures and other aspects such as interpretability, explainability, justifiability and other. During the laboratory classes students work on end-to-end analytical projects developed using SAS Institute systems. This course is one of the courses making it possible to obtain SAS Data Science certificate - a joint certificate by SAS Institute and the Warsaw University of Technology.
More ...This elective course delivered in English (English name: Databases) is offered for MSc in Mathematics students. Unlike the obligatory course in Databases, this course is focused on providing the students with knowledge and skills required to access and process data in databases with emphasis on data analytics. Hence, laboratories are focused e.g. on querying data, rather than developing client applications.
More ...Elective course for PhD students focused on machine learning for data streams, with emphasis on incremental learning and machine learning in nonstationary environments. During this course we discuss how changes happening with time in data distribution and e.g. changes in real decision boundaries in the case of classification tasks can be detected. This is followed by the presentation of machine learning methods for data streams with emphasis on methods detecting concept drift and adapting models to changes in data, e.g. through replacing ensemble members, such as adaptive random forest and other ensemble methods.
More ...Elective course for MSc in Data Science students, focused on machine learning for data streams, with emphasis on incremental learning and machine learning in nonstationary environments. This course is the continuation of Big Data Analytics. Hence, it does not cover the architecture of Big Data systems and non-technical aspects of Big Data analytics.
More ...Warsaw University of Technology Faculty of Mathematics and Information Science Koszykowa 75, Warsaw, Poland
maciej.grzenda at pw.edu.pl
© Stream Mining and Urban Data Systems Group. All Rights Reserved. Designed by HTML Codex