|
|
|
||
Last update: RNDr. Jiří Mírovský, Ph.D. (24.05.2023)
|
|
||
Last update: RNDr. Jiří Mírovský, Ph.D. (23.05.2023)
During the course, students will acquire theoretical knowledge as well as practical skills necessary for solving practical tasks using available data and Artificial Intelligence methods, particularly in the field of text analysis. To this end, they will learn to use tools implemented in the R software system and independently read technical literature. Upon completion of the course, graduates will have the ability to analyze and process data from various areas of the humanities or social sciences, and use this data for experimenting with Artificial Intelligence. |
|
||
Last update: RNDr. Jiří Mírovský, Ph.D. (23.05.2023)
The course will be concluded with an exam. Obtaining the course credit is a prerequisite for taking the exam. The credit is awarded for active participation throughout the term and the submission of ongoing homework assignments. Lab session attendance is mandatory. Lecture attendance is, in fact, essential for understanding the content of the lab sessions and completing the assignments. |
|
||
Last update: RNDr. Martin Holub, Ph.D. (06.06.2023)
|
|
||
Last update: RNDr. Jiří Mírovský, Ph.D. (23.05.2023)
The exam consists of a written and an oral part and we take into account the quality of ongoing homework completions as well. The examination requirements correspond to the course syllabus. More details are available on the course web site. |
|
||
Last update: doc. Mgr. Barbora Vidová Hladká, Ph.D. (24.05.2023)
The teaching is conducted through demonstrations of Artificial Intelligence methods on illustrative solutions of intentionally diverse practical tasks. These tasks include automatic authorship recognition, native language identification, text age estimation, predicting the success of advertising campaigns, analyzing texts from social media, conducting shopping cart analysis, analyzing and visualizing citation networks, visualizing image similarities, and various problems in psychometrics. Students are guided towards independent analysis of data sources from the humanities or social sciences and they acquire the knowledge necessary to use Artificial Intelligence methods implemented in the R software system. We particularly focus on the following topics:
Part I - Introduction to Artificial Intelligence methods General technological principles of Artificial Intelligence and statistical Machine Learning Historical overview of Artificial Intelligence development from a technological and user perspective Statistical data analysis Technologies available for processing textual data Tools from the tidyverse package in the R software system
Part II - Traditional methods of statistical machine learning Principles of learning from examples, classification and regression Use and parameterization of selected learning algorithms Clustering Experiment evaluation
Part III - Deep Learning in Neural Networks Neural Network Architecture Representation of textual data using embeddings Training Neural Networks |
|
||
Last update: RNDr. Jiří Mírovský, Ph.D. (23.05.2023)
We expect students to have a willingness to experiment with Artificial Intelligence, including Neural Networks. Prospective participants of this course should have a basic understanding of working with the R system and should possess at least elementary knowledge of systematic data processing and statistical analysis. These prerequisite requirements can be fulfilled by attending the parallel course "Data Processing and Analysis for Humanities" [NPFL143]. |