Machine Learning Methods (5cr)

Code: R504D139-3001

General information

Enrollment: 02.07.2026 - 31.07.2026; Registration for introductions has not started yet.

Timing: 01.08.2026 - 31.12.2026; The implementation has not yet started.

Number of ECTS credits allocated: 5 cr

Mode of delivery: Contact learning

Teaching languages: english

Seats: 0 - 90

Degree programmes: Machine Learning and Data Engineering

Teachers: Tuomas Valtanen

Teacher in charge: Tuomas Valtanen

Course: R504D139

Evaluation scale

H-5

Objective

You can create a conventional classic machine learning training code solution
You can use a trained machine learning model in conventional programming environments
You can evaluate the differences and strengths of different classic machine learning algorithms
You can optimize your classic machine learning models based on metrics and performance
You are familiar with other uncommon technologies, such as clustering algorithms
You can share your results and exercises via a version control system.

Content

Introduction to machine learning
Classic machine learning: supervised vs unsupervised learning
Regression vs classification: common algorithms
Data preparation and preprocessing
Common error metrics and how to interpret them

Assessment criteria, satisfactory (1)

You can create classic machine learning models with a limited amount of features with your own data and code
You can perform basic data pre-processing tasks in order to train a functional classic machine learning model
You can create conventional error metrics for your machine learning model
You can share your results and exercises via a version control system.

Assessment criteria, good (3)

You can create classic machine learning models with your own data and code
You can perform necessary data pre-processing tasks in order to train a functional classic machine learning model
You can create conventional error metrics for your machine learning model
You can optimize your machine learning model based on data and selected algorithm
You can share your results and exercises via a version control system.

Assessment criteria, excellent (5)

You can create classic machine learning models with your own data and code
You can perform necessary data pre-processing tasks in order to train a functional classic machine learning model
You can create conventional error metrics for your machine learning model
You can optimize your machine learning model based on data and selected algorithm
You can apply advanced algorithms and approaches while optimizing your machine learning model
You can share your results and exercises via a version control system.

Qualifications

Basics of Python programming, Basics of common Python data analytics modules/libraries