EPN-V2

ACIT4630 Advanced Machine Learning and Deep Learning Course description

Course name in Norwegian
Advanced Machine Learning and Deep Learning
Study programme
Master's Programme in Applied Computer and Information Technology
Weight
10.0 ECTS
Year of study
2024/2025
Curriculum
SPRING 2025
Schedule
Programme description
Course history

Introduction

After completing the course, the student is expected to have achieved the following learning outcomes defined in terms of knowledge, skills and competence:

Knowledge

The student

  • has knowledge of similarities and differences between selection in evolutionary biology, behaviour analysis and cultures
  • is familiar with interactions between selection principles at the different levels
  • has broad knowledge of basic principles and theories in modern evolution biology
  • has broad knowledge of key topics in behavioural ecology
  • has knowledge of key topics in modern genetics and understanding of heredity
  • is familiar with the significance of natural selection to the nervous system’s structure and function
  • has knowledge of basic research areas in evolutionary psychology

Skills

The student is capable of

  • using principles of cultural selection in relation to changes in organisations and groups
  • finding examples of how specific behaviour can be explained from an evolutionary perspective
  • reflecting on topics and theories in evolution and behaviour

Competence

The student

  • has insight into the biological basis of behaviour in animals, including humans
  • is capable of describing selection as an explanatory model both orally and in writing
  • is familiar with new ideas and innovation processes in behaviour analysis as a holistic discipline based on selection sciences

Recommended preliminary courses

  • Bachelor level knowledge in linear algebra, vector calculus, and basic statistics, and probability is important for understanding some of the concepts in this course.
  • Knowledge and skills in programming, particularly Python, and machine learning frameworks such as scikit-learn, TensorFlow, and Keras.

Required preliminary courses

Work and teaching methods used in the course are lectures, self-study, presentation of texts and group work. Seminars will also be held where the students present subject matter. Participation in these seminars is compulsory. Students will present texts from the syllabus, encourage discussion and receive guidance on further reading.

During the course, the students must submit three assignments. Submission of the assignments is compulsory.

Learning outcomes

Supervised individual written examination, 4 hours.

Content

This course covers principles of machine learning and deep learning methods and best practices in solving problems effectively. Most of the problems are related and applicable in various areas such as computer vision, surveillance, assistive technology, medical imaging, etc. Therefore, the course intends to provide case studies and examples of ML and DL in solving various problems. Students can explore the tremendous potential of modern AI, ML, and DL methods and techniques in solving problems in different application domains through project work.

Teaching and learning methods

Supervised individual written exam, 4 hours.

Course requirements

None

Assessment

Grade scale A-F

Permitted exam materials and equipment

One internal and one external examiner

Grading scale

Two internal examiners

Examiners

Two internal examiners. External examiner is used periodically.

Course contact person

Associate Professor Raju Shrestha