spring 2022
DTE-3608 Artificial Intelligence and Machine Learning - 5 ECTS

Last changed 24.08.2022

Application deadline

Applicants from Nordic countries: December 1st. Exchange students and Fulbright students: October 1st.

Type of course

The course may be taken as a single course.

Admission requirements

A relevant undergraduate Bachelor Engineering program with minimum 25 credits mathematics, 5 credits statistics, 7,5 credits physics.

Application code: 9371

The student should be knowledgeable in programming with insight in Python scripting This course requires basic insight in artificial intelligence and machine learning and will build on:  MAT-3802 1 Discrete Mathematics with Game- and Graph Theory DTE-2501 AI Methods and Applications DTE-2502 Neural Networks DTE-2602 Introduksjon Maskinlæring og AI


Course content

  • The students will be introduced to AI as a discipline and scientific research areas and understand its industrial and societal impact
  • The student will acquire insight in advanced topics in artificial intelligence and their applications covering, but not limited to, advanced reasoning, ontologies, supervised and non-supervised learning, multi-agent architectures and operations,  evolutionary methods, swarms and colonies.
  • Applications within health and welfare, robotics, industry 4.0, smart citry, smart energy, traffic, commodity and financial trading will be treated
  • The student will work hands-on to develop applications were theoretical concepts are tested out
  • The subject of information management and decision theory with scarce or corrupted data will be treated.
  • Data sharing and data market design for AI will also be treated.
  • AI and ethics is going to be an essential part of the course

Recommended prerequisites

DTE-2501 AI Methods and Applications, DTE-2502 Neural Networks, DTE-2602 Introduction to Machine Learning and AI, MAT-3802 Discrete Mathematics with Game- and Graph Theory

Objectives of the course

After passing this course the student should have obtained the following learning outcome:

Knowledge

The student shall have;

  • A deep insight in Artificial Intelligence and its applications
  • Deep knowledge of symbolic and numerical methods
  • An intimate understanding og how to apply Artificial Intelligence in different types of applications
  • Knowledge of how to deal with massive, incomplete, compromised and qualitative data
  • Intimate knowledge of supervised learning algorithms such as CNN, LSTM, XGBoost and associated training concepts
  • Intimate knowledge of advanced reinforcement learning, profit sharing and similar
  • Intimate knowledge of multi-objective optimization and learning with genetic algorithms
  • Knowledge of colonies and swarms and how they learn

Skills

The student should be able to;

  • To program AI and machine learning algorithms
  • Create simple diagnostic and reasoning systems
  • Create regression and classificatition systems
  • Create advanced learning systems
  • Create data processing trains based on Internet of Things

General Competence

  • The student will be able to contribute effectively in industrial AI and machine learning projects
  • The student will have sufficient knowledge to pursue self-studies in specific AI and machine learning topics.

Language of instruction and examination

English

Teaching methods

40 hours of lectures and hands-on class exercises

30 hours of self-study exercises with guidance to be handed in for approval

Lectures will be held in English (Provided the presence of English speaking students, English will be chosen).

Lecture notes will be given in English.

Written examination will be in English


Information to incoming exchange students

This course is open for inbound exchange student who meets the admission requirements. Please see the Admission requirements" section".

Master Level

Do you have questions about this module? Please check the following website to contact the course coordinator for exchange students at the faculty: INBOUND STUDENT MOBILITY: COURSE COORDINATORS AT THE FACULTIES | UiT


Assessment

Written examination typically including rapid prototyping in python

Letter grading A - F, where F is fail grade.

There will be arranged a re-sit exam for this course.


Schedule

  • About the course
  • Campus: Narvik |
  • ECTS: 5
  • Course code: DTE-3608
  • Tidligere år og semester for dette emnet