Artificial Intelligence - Methods and Applications, 7.5 Credits

Contents

Modern intelligent systems and robots are transforming the daily life of society. These kind of systems are designed and implemented considering Artificial Intelligent (AI) models and algorithms. This course aims to present different AI theories and algorithms in order to give a solid background in the area, as well as practical knowledge about how to implement real intelligent  systems. The main theme of the course is theories and algorithms from classical AI and intelligent robotics. During the course, the students will acquire knowledge about different paradigms of AI, e.g. logic-based and data-driven methods, rational intelligent agents, as well as theoretical and practical knowledge about robotics topics like navigation and motion planning.
 
The course consists of two parts:
Part 1 theory, 4.5 credits
Topics covered:

• Heuristics for search.
• Search for games.
• Applied first-order logic.
• Classical planning: heuristics.
• Knowledge representation.
• Probability theory: axioms, conditional probability, Bayes’ rule.
• Bayesian networks.
• Probabilistic reasoning over time.
• Hidden Markov Models.
• Decision trees.
• Reinforcement learning.
• Multi-agent systems.
• Robotics: hybrid architectures, motion planning, metric and topological route planning, localization and map generation.

Part 2, laboratory, 3 credits.
In the laboratory part some of the theories and techniques discussed in the theoretical part are put into practice. This part consists of two mandatory laboratory assignments, in part carried out with physical robots or advanced simulators.

Expected learning outcomes

Knowledge and understanding
After having completed the course the student should be able to:

• Describe and apply concepts, methods, and theories of search, heuristics, games, knowledge representation, planning (FSR 1)
• Describe and apply concepts, methods, and theories of logic and probability theory and to analyze the power and limitation of their use for knowledge representation and reasoning systems (FSR 2)
• Describe methods and theories of probabilistic reasoning (e.g. Bayesian networks), probabilistic reasoning over time (e.g. Hidden Markov Models), Probabilistic Planning (e.g. Markov Decision Processes), and learning methods (e.g. decision trees, reinforcement learning, Bayesian learning) (FSR 3)
• Describe and apply methods and theories for hybrid architectures, motion planning, topological and metric route planning, and localization and map generation (FSR 4) 

Skills and abilities
After having completed the course the student should be able to:

• Design, construct, and evaluate intelligent software agents (FSR 5)
• Apply concepts for adversarial search and construct good heuristics (FSR 6)
• Demonstrate theoretical and practical skills in developing intelligent software agents based on data-driven and logic-based methods. (FSR 7)
• Create hybrid architectures for robots able to autonomously navigate and map the environment (FSR 8) 

Values and attitudes
After having completed the course the student should be able to:

• Discuss the effect on society of emerging technologies in AI (FSR 9)
• Evaluate different AI-based technologies using the knowledge gained during the course (FSR 10)

Required Knowledge

Univ: To be admitted you must have (or equivalent) 90 ECTS-credits including 60 ECTS-credits in Computing Science or two years of completed studies within a study programme (120 ECTS-credits). In both cases, the studies must include the course Fundamentals of Artificial Intelligence (5DV121), at least 7.5hp within Data Structures and Algorithms (e.g. 5DV149 or 5DV150) and at least 7.5 ECTS-credits within logic (e.g. 5DV102 or 5DV162). A Bachelor's degree with a major in Computer Science is considered to be equivalent.

Proficiency in English equivalent to Swedish upper Secondary course English A/5. Where the language of instruction is Swedish, applicants must prove proficiency in Swedish to the level required for basic eligibility for higher studies.

Form of instruction

Instruction consists of lectures and mandatory computer based assignments. In addition to scheduled activities, individual work with the material is also required.

Examination modes

The examination of Part 1 (FSR 1-4, 9-10) consists of a written exam in halls. The grades given are Fail (U), Pass (3), Pass with Merit (4), or Pass with Distinction (5).
 
The examination of Part 2 (FSR 5-8) consists of two mandatory assignments, each of which is described in a written report. In Part 2 the grades given are Fail (U), Pass (G).
 
On the course as a whole, the grades given are Fail (U), Pass (3), Pass with Merti (4), or Pass with Distinction (5). The overall grade is primarily based on the written exam. In order to pass the course completely, all mandatory parts must be passed. For all students who do not pass the regular examination there are additional opportunities to do the examination.
 
A student who has passed an examination may not be re-examined.
 
A student who has taken two tests for a course or a segment of a course, without passing, has the right to have another examiner appointed, unless there exist special reasons (Higher Education Ordnance Chapter 6, Section 22). Requests for new examiners are made to the head of the Department of Computing Science.
 
Examination based on this syllabus is guaranteed for two years after the first registration of the course. This applies even if the course is closed down and this syllabus ceased to be valid.

Transfer of credits
Students have the right to be tried on prior education or equivalent knowledge and skills acquired in the profession can be credited for the same education at Umeå University. Application for credit is submitted to the Student Services / Degree. For more information on credit transfer available at Umeå University's student web, www.student.umu.se, and the Higher Education Ordinance (Chapter 6). A refusal of crediting can be appealed (Higher Education chapter 12) to the University Appeals Board. This applies to the whole as part of the application for credit transfer is rejected.

Other regulations

In an exam this course may not be included, in whole or in part, simultaneously with another course of similar content. If in doubt, consult the student counselors at the Department of Computer Science.

Specifically, this course cannot be included in a degree together with 5DV122 Artificial Intelligence - Methods and Applications. The overlap between the courses is 7.5 credits.

Course connections to programmes and degrees
The course is a central course in the Master's Programme in Computing Science and the Master's Programme in Robotics and Control.

The course can be part of the fulfilment

• of 45 credits (at least 37.5 of these on advanced level) within Computer Science when pursuing the specialization in Computer Science within a degree of Master of Science (Two Years) with Computing Science as Main Field of Study.
• of 60 credits on advanced level within Robotics and Control when pursuing the specialization in Robotics and Control within a degree of Master of Science (Two Years) with Computing Science as Main Field of Study.