course

At the end of this course, students are expected to generate knowledge from various types of data, applying the process of “knowledge discovery in databases”, with emphasis on the main techniques of Data Mining (data cleaning, classification, clustering). , association analysis, etc.). The students will have the opportunity to identify and select the basic analysis techniques that, according to the criteria presented in the course, are best applied to the objective of generating knowledge, according to the domain of the problem proposed. For this, cases that incorporate problems and data from areas as diverse as, for example, Astronomy, Economics, Medicine, Marketing, Social Networks, among others, will be analyzed. It is also expected to bring the students closer to the problem of the analysis of large volumes of data and that they can acquire more advanced techniques on these topics. It is an introductory course, where the examples are referential and the students for their semester work choose an area of ​​interest, to which the standard methodology of data mining is applied. The students will identify the problem of overfitting in information processing models that prevent an objective analysis of the data. Finally, they will develop ethical skills for professional performance in the field of Data Engineering.

The objective of the course is to introduce students to the area of learning based on deep neural networks, commonly known as Deep Learning. The techniques used in this area have been fundamental in the latest advances in Artificial Intelligence, particularly in tasks such as natural language processing and computer vision. During the course, the student will be exposed to the theory behind Deep Learning models, will understand how they work, their possible uses, and will be able to build and train models that allow them to solve real problems.

The purpose of the Natural Language Processing course is to introduce students to the discipline of natural language processing (NLP). The student will use this method to solve tasks, with delimited solutions regarding their relevance and size. This discipline studies the design of methods and algorithms that receive as input and/or produce as output data in the form of natural language (e.g., text, voice). The course focuses on text processing although applications in speech processing are mentioned.

The purpose of this course is to introduce students to statistical thinking, a systematic way of thinking to describe “real world” phenomena taking into account their inherent uncertainty and using data for decision making. The course introduces the fundamentals of statistical thinking, which are descriptive data analysis, statistical programming in R, and probability theory. It then teaches the two most important schools of statistical inference: frequentist inference and Bayesian inference. Finally, advanced topics such as model evaluation using information theory, directed graphical models for modeling conditional dependencies between variables, and multilevel models are discussed.