Text

Course syllabus - Applied Machine Learning

Scope

7.5 credits

Course code

DVA263

Valid from

Autumn semester 2026

Education level

First cycle

Progressive Specialisation

G1F (First cycle, has less than 60 credits in first-cycle course/s as entry requirements)

Main area(s)

Computer Science

Organisation

Department of Computer Science & Engineering

Ratified

2022-01-24

Revised

2025-11-03

Literature lists

Course literature is preliminary up to 8 weeks before course start. Course literature can be valid over several semesters.

    • Ratified date: 2023-09-11
    • Latest update: 2025-05-27

    Books

    Géron, Aurélien

    Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: concepts, tools, and techniques to build intelligent systems

    ISBN: 9781492032649

    LIBRIS-ID: kwlh71x0hxh5fbf2

    Second edition, Sebastopol, CA, O'Reilly Media, Inc., xxv, 819 pages

    Mandatory

Objectives

The goal of the course is to provide knowledge on machine learning techniques with a focus on its application that includes data, feature engineering, machine learning and deep learning models, and model evaluation.

Learning outcomes

After completing the course, the student should be able to:

  1. describe the fundamental needs, challenges and limitations of data and feature engineering,
  2. demonstrate the ability to analyse trade-off between different machine learning models and
  3. describe and understand the basic techniques of ML model evaluation and improvement.

Course content

Module 1: Learning from Data.
Module 2: Representing Data and Feature.
Module 3: Supervised Machine Learning: Naive Bayes Classifiers, Ensembles of Decision Trees (RF) and Support Vector Machines.
Module 4: Neural networks and Deep learning.
Module 5: Unsupervised Machine Learning: PCA, t-SEN, Agglomerative Clustering, DBSCAN.
Module 6: Model Evaluation, Improvement, and ethical aspects.

Specific requirements

Discrete Mathematics 7.5 hp, Object Oriented Programming 7.5 hp, Machine Learning Concepts 7.5 hp, Basic Vector Algebra 7.5 hp or equivalent.

Examination

Written assignment (INL1), Comparison of the performance of different supervised models, 1,5 credits, examines the learning outcome 2, marks Fail (U) or Pass (G).
Written assignment (INL2), Problem solving with unsupervised learning, 1 credit, examines the learning outcome 2, marks Fail (U) or Pass (G).
Written assignment (INL3), Neural networks and Deep learning, 2 credits, examines the learning outcome 2, marks Fail (U) or Pass (G).
Project (PRO1), Project report, 3 credits, examines the learning outcome 1-3, marks Fail (U), 3, 4 or 5.

A student who has a certificate from MDU regarding disability study support, can request adaptions for the examination. It is the examiner who takes decisions on any adaptions, based on the certificate and other conditions.

Grade

Grading scale: 5, 4, 3

Interim Regulations and Other Regulations

The course overlaps 1.5 credits with DVA76 Deep Learning for Industrial Imaging and DVA453 Machine Learning With Big Data.