Warning
This page is located in archive. Go to the latest version of this course pages. Go the latest version of this page.

B(E)3M33UI - Artificial intelligence

The course deepens and enriches knowledge of AI gained in the bachelor course Cybernetics and Artificial Intelligence. Students will get an overview of other methods used in AI, and will get a hands-on experience with some of them. They will master other required abilities to build intelligent agents. By applying new models, they will reiterate the basic principles of machine learning, techniques to evaluate models, and methods for overfitting prevention. They will learn about planning and scheduling tasks, and about methods used to solve them. The student will also get acquainted with the basics of probabilistic graphical models, Bayesian networks, and Markov models, and will learn their applications. Part of the course will introduce students to the area of again popular neural networks, with an emphasis on new methods for deep learning.

Lectures | Literature | Labs | Projects | BRUTE | Forum | Prerequisities

  • Master study program Cybernetics and robotics, compulsory course of Robotics branch.
  • The course is finished with an assessment and an exam.
  • After completion of this course, students get 6 credits.
  • For an average student, this corresponds to 2 hours of lecture, 2 hours of labs and 5-6 hours of work at home each week!

Assessment requirements

  • At most 2 absences in computer labs will be tolerated.
  • During the semester, students can gain up to 40 points for two semestral projects.
    • For the semestral projects, students must hand in their solutions (report and/or program code).
    • Late policy: late solutions will be penalized by 2 to 4 points for each started week of delay (details in BRUTE).
  • Students must get at least 20 points to get the assessment and be allowed to enter the exam.

Exam

During the semester, including the exam, students can get at most 100 points: 40 points for the semestral projects and 60 points for the exam. To successfully pass the exam, students need to get at least 30 points out of 60, i.e. 50 %.

  • We do not provide exam test examples.
  • But we will provide list of competencies which can serve as a list of possible exam questions.

Grading

We use the usual grading table:

Points >=90 <80, 90) <70, 80) <60, 70) <50, 60) (0, 50)
Grade A B C D E F

Contacts

Lecturers: Petr Pošík, Radek Mařík

Lab instructor: Jiří Spilka

courses/ui/start.txt · Last modified: 2019/02/15 14:35 by xposik