IT3030 - Deep Learning


Examination arrangement

Examination arrangement: Portfolio assessment
Grade: Passed/Failed

Evaluation form Weighting Duration Examination aids Grade deviation
work 25/100
work 25/100
work 25/100
work 25/100

Course content

The course is a follow-up to TDT4173 Machine Learning. It gives thorough coverage of deep learning. The course covers both mathematical and computational foundation for deep learning, practical applications such as processing of images, text, and other modalities. In addition, deep reinforcement learning will be discussed. Modern software frameworks for deep learning will be introduced.

Learning outcome

General principles for learning/adaptive systems
Mathematical and computational foundation for deep learning
How to use deep learning in diverse practical applications

Analyze different frameworks for deep learning in specific application domains
Ability to analyze the mathematical foundation for diverse deep learning published in the literature
Build computational systems that achieve deep learning

General competences:
Understand deep learning's basis in mathematics and cognitive science
Understand possibilities and limitations of deep learning in practical settings

Learning methods and activities

Lectures, self study

Further on evaluation

Grade is based on portfolio assessment. All projects must be done individually and must be completed to pass the course. Results for each part are given as percentages, while the final grade is in pass/fail. Note that there is no re-sit exam in this course. Repetition of assessment is only possible in the teaching semester.

Specific conditions

Admission to a programme of study is required:
Computer Science (MIDT)
Computer Science (MTDT)
Industrial Economics and Technology Management (MTIØT)
Informatics (MIT)
Informatics (MSIT)

Required previous knowledge

TMA4115 Mathematics 3, TDT4120 Algorithms and data-structures, TDT4171 Methods in Artificial Intelligence, and TDT4173 Machine learning.

Course materials

Ian Goodfellow, Yoshua Bengio and Aaron Courville: Deep Learning (2016). MIT Press.
Supplementary articles will be handed out as needed.

More on the course



Version: 1
Credits:  7.5 SP
Study level: Second degree level


Term no.: 1
Teaching semester:  SPRING 2021

No.of lecture hours: 2
Lab hours: 6
No.of specialization hours: 7

Language of instruction: English

Location: Trondheim

Subject area(s)
  • Computer Science
  • Computer Systems
Contact information
Course coordinator: Lecturer(s):

Department with academic responsibility
Department of Computer Science



Examination arrangement: Portfolio assessment

Term Status code Evaluation form Weighting Examination aids Date Time Digital exam Room *
Spring ORD work 25/100
Room Building Number of candidates
Spring ORD work 25/100
Room Building Number of candidates
Spring ORD work 25/100
Room Building Number of candidates
Spring ORD work 25/100
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