Sök i kursutbudet

Använda sökfunktionen för att hitta i Chalmers utbildningsutbud, både vad gäller kurser och program. När det finns en kurshemsida visas en hus-symbol som leder till denna sida. Tänk på att välja det läsår du vill se information om.
Sök program och utbildningsplaner


Institutionernas kurser för doktorander

​​​​​​​​​​​​​​​​​​​​

Kursplan för

Läsår
TIN171 - Artificial intelligence
 
Kursplanen fastställd 2009-02-25 av programansvarig (eller motsvarande)
Ägare: MPALG
7,5 Poäng
Betygskala: TH - Fem, Fyra, Tre, Underkänt
Utbildningsnivå: Avancerad nivå
Huvudområde: Datateknik, Informationsteknik
Institution: 37 - DATA- OCH INFORMATIONSTEKNIK


Undervisningsspråk: Engelska

Modul   Poängfördelning   Tentamensdatum
Lp1 Lp2 Lp3 Lp4 Sommarkurs
0107 Tentamen 7,5 hp Betygskala: TH   7,5 hp   Kontakta examinator

I program

MPSEN SOFTWARE ENGINEERING AND TECHNOLOGY, MSC PROGR, Årskurs 1 (valbar)
MPSYS SYSTEMS, CONTROL AND MECHATRONICS, MSC PROGR, Årskurs 1 
TKDAT DATATEKNIK, CIVILINGENJÖR, Årskurs 3 (valbar)
MPALG COMPUTER SCIENCE - ALGORITHMS, LANGUAGES AND LOGIC, MSC PROGR, Årskurs 1 (obligatorisk)
MPCAS COMPLEX ADAPTIVE SYSTEMS, MSC PROGR, Årskurs 2 (valbar)
MPIDE INTERACTION DESIGN, MSC PROGR, Årskurs 1 (valbar)
TKITE INFORMATIONSTEKNIK, CIVILINGENJÖR, Årskurs 3 (valbar)

Examinator:

Docent  K V S Prasad


Ersätter

TIN170   Artificiell intelligens


  Gå till kurshemsida

Behörighet:

För kurser inom Chalmers utbildningsprogram gäller samma behörighetskrav som till de(t) program kursen ingår i.

Kursspecifika förkunskaper

Good to very good programming skills. Knowledge of traditional AI language such as Lisp or Prolog is not necessary. The course project can be done, for example, in C, C++, Java, Haskell, Lisp or Prolog. Having taken the courses TIN092 Algorithms and DAT060 Logic in computer science is helpful but not mandatory.

Syfte

Artificial Intelligence (AI) is a field of computer science that studies how computers can accomplish tasks that were traditionally thought to require human intelligence. The aim of this course is to give a deepened understanding of the possibilities and the limitations of AI methods.

Lärandemål (efter fullgjord kurs ska studenten kunna)

After successful completion of the course participants will have obtained the following skills:
Awareness of the most important methodologies used in the field of AI, when to use them and when not to use them. You should be able to judge what can be achieved by AI technology and what is not possible.
In-depth knowledge of the most important systematic and heuristic general search algorithms used in AI. You should be able to judge when to use which algorithm. You should be able to program these algorithms yourself.
Basic knowledge in the specific AI subfields of Machine Learning, Language Understanding, Automatic Reasoning and Planning. You are aware of the fundamental algorithms in these areas and how they are used.
In-depth and active knowledge in at least one of the areas mentioned in the previous item gained by a supervised group project. You should be able to read and understand research literature in the area of your specialization. You should be able to design, program, document, and evaluate a small AI-based software system on your own so that it has acceptable performance. You should be able to apply your knowledge to a new problem.

Innehåll

The course is taught in a project-oriented way. In concrete terms, this means that in the beginning is a block of eight lectures that cover the most important AI methodologies. Current topics are:

- Introduction to AI
- Uninformed Search
- Informed Search
- Game Search
- Machine Learning and Information Retrieval
- Logic and Deduction
- Planning
- Natural Language Dialogue Systems

Starting in the third course week (and overlapping with the lectures), students choose course project where they are required to design and implement an AI agent. The can choose one of three concrete projects, typically from the subareas Planning, Machine Learning, Deduction or Natural Language Dialogue Systems. The project is done in groups of 4 or 5 students.

From course week three until the end of the course each project group can book one supervision session with the teachers per week.

Organisation

The course consists of two parts: in the first part an introduction into the main topics and techniques of Artificial Intelligence (AI) is provided as a block of lectures. In the second part, you will analyse, design, and implement a real AI project yourself as a member of a small team. Each team obtains weekly counsel from one of the teachers. You will be able to choose one out of three projects that matches your interests. The programming language can be freely chosen.

Litteratur

Stuart Russell, Peter Norvig, Artificial Intelligence: A Modern Approach. Second Edition. Prentice Hall 2003.

Examination

In order to pass the course, the following is necessary:

- Participate in at least three supervision sessions. One of these must take place in course week 3 or 4.
- Active participation in a demo session in the final course week, where prototypes of the developed systems are presented.
- Submission of the documented source code of the developed program. The program must be runnable and successfully implement an AI agent.
- Submission of a written report that explains theory and implementation of the chosen project.
- Each group member must defend his contribution during a group-wise oral exam scheduled in the exam week after the course ends.

The final grade is composed equally on the performance of the submitted program, the quality of the written report, and the answers in the oral exam.


Sidansvarig Publicerad: må 13 jul 2020.