Emneplan forDAVE3625 Introduksjon til Kunstig Intelligens

This course provides a broad introduction to Artificial Intelligence (AI), with methodologies and techniques that can be applied to different application domains. The course will balance theoretical approaches and practical tasks. Two broad AI areas will be covered, namely supervised and unsupervised methods. Among those, standard methods for regression, classification and clustering will be covered, e.g. support vector machines, nearest neighbor, decision tree, K-means, agglomerative and hierarchical clustering. An introduction to the usage of artificial neural networks and backpropagation algorithm will be provided.

Basic programming skills (C, Python, Java, or similar programming language)

Discrete mathematics course at undergraduate level

None

On successful completion of the course, the student should have the following learning outcomes defined in terms of knowledge, skills and general competence.

Knowledge

The student:

• Knows how the field of artificial intelligence developed historically

• Is familiar with the main artificial intelligence theories and has a practical understanding of the development and use of artificial intelligence

• Can reflect on the practical, social and ethical implications of the development of artificial intelligence

• Has an understanding of the current application areas of artificial intelligence

Skills

The student:

• Has the theoretical and practical skills to build simple artificial intelligence systems

• Can use a variety of state-of-the-art artificial intelligence techniques in different application domains

• Can evaluate the technical quality and practical value of various types of artificial intelligence

Competence

The student:

• Has both theoretical and practical understanding of artificial intelligence methods

• Can discuss the relevance, strengths and limitations of artificial intelligence methods

• Is able to solve real-life problems using artificial intelligence methods

The course consists of lectures and seminars on techniques and methods, as well as a project to be carried out in groups of 2 to 4 students. The project will be chosen from a portfolio of available problems, either from industry partners or by the research groups. The students will work in groups and will submit an academic report and give an oral presentation. Lab sessions supporting the assignments will be provided.

3 compulsory assignments done in groups of 2-4 students must be approved in order to be admitted to the final exam.

1. 30% of the grade based on the academic report (in groups of 2-4 students, 5-10 pages written report with link to code e.g. on github).

2. 70% of the grade based on individual written examination (3 hours).

Both exams must be passed in order to pass the course.

The exam result can be appealed.

No support materials are allowed for the written exam.

A grading scale of A (highest) to F (lowest) where A to E is a pass grade and F is a fail grade.

Two examiners. External examiner is used periodically.