Introduction to Practical Machine Learning

General content

This course gives an intuitive introduction to machine learning both in theory and practice.

The course has three parts.

The first is a brief, introductory lecture to the software “R”, which will be used to han-dle the practical examples of data management and machine learning.

The second part will cover “Machine learning: What is it?” and describe how it allows the discovery of knowledge from data. Since data is the fuel that drives machine learning, we will dive into data management where descrip-tion of organization, storage, cleansing, filtration, and preparation of data collected and used in re-search projects will be explained. In machine learning, multiple topics including data as a source for future decision-making, supervised and unsupervised learning techniques will be covered.

The third part includes a group project where PhD candidates will work together on datasets, either of their choice (i.e., PhD-related) or open datasets, and apply machine learning techniques to distill in-teresting patterns and knowledge. Candidates will be given 3 weeks to work on the project and pre-sent their results in the class.

Type of course

Methods

General learning objective

After completion of the course, the PhD candidates will be able to conceptualize the different types of machine learning. Candidates will be able to begin writing and executing R scripts, filter, manage, and clean data as well as apply machine learning techniques on datasets.

Knowledge

After completion of the course, the candidate…

• understands the theoretical foundation of machine learning
• understands the differences between various machine learning techniques
• is capable of performing various machine learning techniques

Skills

After completion of the course, the candidate…

• can get open datasets, clean, and filter data to perform machine learning
• can prepare data that is suitable for particular machine learning techniques
• can perform supervised and unsupervised machine learning techniques such as clustering, regres-sion, and text mining

General competence

After completion of the course, the candidate…

• has acquired solid competence on how to best apply and communicate findings of machine learning approaches to the broad audience.

Sping or Autumn.

The course will given in Spring 2026. Please check the IGSIN homepage for an overview of when and where the course is planned next time. IGSIN: International Graduate School in Interdisciplinary Neuroscience | University of Bergen