FI:PV212 Seminar on ML, NLP, and IR - Course Information

PV212 Seminar on Machine Learning, Language Representation and Information Retrieval

Extent and Intensity

0/2/0. 2 credit(s) (plus extra credits for completion). Type of Completion: k (colloquium).
In-person direct teaching

Teacher(s)

doc. RNDr. Petr Sojka, Ph.D. (lecturer)

Guaranteed by

doc. RNDr. Petr Sojka, Ph.D.
Department of Visual Computing – Faculty of Informatics
Contact Person: doc. RNDr. Petr Sojka, Ph.D.
Supplier department: Department of Visual Computing – Faculty of Informatics

Timetable

Thu 19. 2. to Thu 14. 5. Thu 10:00–11:50 A502

Prerequisites

SOUHLAS
Interest in research problems in areas of Machine Learning, Scientific Visualization, Information Retrieval and Digital Typography. Courage to learn how to move the human knowledge and understanding in these areas by CS research. Willingness to study particular topic of choice, and refer, discuss and brainstorm about it with others.

Course Enrolment Limitations

The course is also offered to the students of the fields other than those the course is directly associated with.

fields of study / plans the course is directly associated with

there are 34 fields of study the course is directly associated with, display

Abstract

The aim of the seminar is to give students (both pre- and post-graduates) the opportunity to read, practice, and present scientific results (either their own or those acquired from scientific papers. Every student will have her/his own presentation in the seminar.

Learning outcomes

At the end of the course students will have experience in presenting and discussion of their or other (from readings) research. They also will be able to prepare scientific presentation of their work (slides, thesis), and communicate scientific results.

Key topics

Programme and referred topics/projects for each year will be posted on the course's web page, and presentations will be negotiated with registered students. The lectures consist mostly of students' presentations. The presentations and discussion are in English. The students will have ample time for discussion after each presentation.

Study resources and literature

• WITTEN, I. H. and Eibe FRANK. Data mining : practical machine learning tools and techniques. 2nd ed. Amsterdam: Elsevier, 2005, xxxi, 525. ISBN 0120884070. info
• KNUTH, Donald Ervin. Digital typography. Stanford: Center for the Study of Language and Information, 1999, xv, 685. ISBN 1575860112. info

Approaches, practices, and methods used in teaching

Lectures are interspersed with seminar-style discussions and brainstorming to solve the reported research problems or thesis topics. Students will be given readings as preparation for the contact teaching hours if they do not bring their own research problems.

Method of verifying learning outcomes and course completion requirements

Each student must prepare and deliver one short lecture (to discuss a research topic from the readings or to solve a project typical of their thesis) and present their solution during the term.
Students should also actively participate in the discussions.

Language of instruction

English

Follow-Up Courses

• DUVOD Introduction to PhD Study
• PV173 Lab Seminar – NLP
• PV174 Lab Project – Electronic and MultiMedia Applications

Study support

https://www.fi.muni.cz/~sojka/PV212/

Further comments (probably available only in Czech)

Study Materials
The course is taught each semester.

Teacher's information

https://www.fi.muni.cz/~sojka/PV212/

• Enrolment Statistics (recent)
  
• Permalink: https://is.muni.cz/course/fi/spring2026/PV212