DAT200 Applied Machine Learning
There may be changes to the course due to to corona restrictions. See Canvas and StudentWeb for info.
Showing course contents for the educational year 2021 - 2022 .
Course responsible: Kristian Hovde Liland
Teachers: Oliver Tomic
ECTS credits: 10
Faculty: Faculty of Science and Technology
Teaching language: EN
Teaching exam periods:
The starts in the spring parallel.
The course will be taught / graded in the spring parallel.
Course frequency: Annually
First time: 2017H
Introduction to basic machine learning methodology using modern, powerful computing tools. The methodology covered includes:
- preprocessing and arranging of data: feature extraction (PCA, LDA), feature selection/importance, visualisation, scaling, formatting of data types.
- clustering: among other K-meansclassification: KNN, logistic regression, LDA, SVM, decision trees
- regression: OLS, regularisation, polynomial regression, tree based methods, PCR, PLS
- strategies for model validation and parameter optimisation
The course will give an introduction to the basic theoretical properties of the methods, but has main focus on applied modelling using real data. The students will learn to build effective and accurate models that, depending on the application, can contribute to several of UN's sustainability goals, among others 3, 11, 12, 14, 15.
Skills and insight into basic techniques for machine learning. Basic understanding of various models' mathematical properties and operations. The student will learn to master analysis methods suited for 1) Explorative data analysis (diagnose and visualisation), 2) Pre-processing of data from various sources, 3) Modelling and prediction med continuous and categorical responses (regression and classification) and validation of predictive models.
The student will learn to connect problems with choice of appropriate analysis methods.
The course will consist of lectures and practical exercises using computers and modern machine learning software (with help from teaching assistants).
Machine learning is a subject that constantly evolves, and online learning resources will be connected to lectures and exercises through the course webpages in Canvas.
The students can also request appointments with the lecturer in his/her office on pre-arranged times and via email.
Curriculum, programs, supporting literature, etc. will be announced on the course web page.
DAT110 (former MATH-INF110), alternatively STAT100 or similar.
MATH113/MATH131 or similar basic linear algebra.
INF120 or a similar course in basic programming (skills in Python are required).
INF200 or a similar course in advanced programming (version control and good programming practice is assumed known)
MATH280 should be taken in parallel.
Obligatory hand-in assignments. Rules for approving obligatory activities will be announced when the course starts.
Written exam, 3.5 hours. A-F.
Lectures: 78 hours. Exercises: 26 hours. Colloquia and self study: 146 hours
Type of course:
Lectures: 4 hours per week. Exercises: 2 hours per week.
An external censor will participate together with the internal censor in forming the exam and censor guide. The external censor checks the internal censor's assessment of a random selection of candidates as a calibration at certain intervals in line with the faculty's guidelines for grading.
Allowed examination aids: A1 No calculator, no other aids
Examination details: Written exam: A - E / F