PROG2051 - Artificial Intelligence


Examination arrangement

Examination arrangement: Aggregate score
Grade: Letters

Evaluation Weighting Duration Grade deviation Examination aids
Project 60/100
Mandatory assignments 40/100

Course content

The subject focus on data-driven AI topics including machine learning, Bayesian networks, deep learning and we will look at popular and successful applications of these techniques in image processing and natural language processing. Practical applications and real world examples will be carefully walked through so that the students can finish a complete AI project in a reasonable size. Lab exercises, and obligatory assignments are important instruments to ensure learning progress with well-defined milestones. 

This course replaces the original IMT 3104 Artificial Intelligence.

Learning outcome

On successful completion of the module, students will be able to: * Understand and evaluate various core techniques and algorithms of AI, including regression, machine learning, Markov decision process, and Bayesian networks. Understand the meaning of concepts such as intelligence, classification, clustering and decision-making. * Identify different uses and applications of AI techniques and algorithms, from neuroscience, understanding brain to image processing, natural language processing, and other types of data different application domains. * Implement several of the algorithms on different AI problems. The students will also enhance their programming skills in a preferred language of their own by learning to program AI algorithms. * Improve programming skills through the programming of AI algorithms. Programming exercises and assignments help enhancing the understanding the theory learnt in class. * Evaluate the run-time and memory complexity of several AI algorithms, and practice with creating better algorithms.

Learning methods and activities

Lectures, lab exercises, self-study and obligatory assignments. This course will focus on the practical implementation of AI concepts. Lectures will introduce a topic area, and students are expected to implement and report on the key concept.

Further on evaluation

*Evaluation* Group course project (report and source codes) (60%) 4 compulsory assignments (40%). Each of these assignments must be passed individually to be able to start the course project. Both parts must be passed. *Resit exam* Re-sit examination for the course project may be changed to oral exam. The assignments must be taken the next time the course is running. 

Specific conditions

Admission to a programme of study is required:
Computer Science (BIDATA)
Programming (BPROG)

Required previous knowledge

IMT2021 Algoritmiske metoder

REA1101 Matematikk for informatikkfag eller REA2091

Course materials

- History and overview of AI - Bayesian networks - Machine learning - Deep learning - Machine learning for image processing - Natural language processing - Other AI topics

More on the course



Version: 1
Credits:  7.5 SP
Study level: Third-year courses, level III


Term no.: 1
Teaching semester:  SPRING 2022

Language of instruction: English

Location: Gjøvik

Subject area(s)
  • Informatics
Contact information
Course coordinator: Lecturer(s):

Department with academic responsibility
Department of Computer Science


Examination arrangement: Aggregate score

Term Status code Evaluation Weighting Examination aids Date Time Examination system Room *
Spring ORD Mandatory assignments 40/100 INSPERA
Room Building Number of candidates
Spring ORD Project 60/100 INSPERA
Room Building Number of candidates
  • * The location (room) for a written examination is published 3 days before examination date. If more than one room is listed, you will find your room at Studentweb.

For more information regarding registration for examination and examination procedures, see "Innsida - Exams"

More on examinations at NTNU