Please note that these courses have been organised in 2023. Courses for 2024 have not yet been selected.
Information for 2024 will be updated at a later date.
Department of Environmental and Biological Sciences:
Resilience of Forest to Climate Change
Course dates: 7-18 August 2023 ( 2 weeks)
Course extent: 5 ECTS
Course coordinator: Frank Berninger (email@example.com)
Course description in Peppi: LY00DE69
Effect of climate change on northern ecosystems, carbon balances of forest soils, remote sensing of ecosystem change, modelling of climate change responses using empirical models, field measurements of forest stands, open data resources for climate change, spectral responses of plants in response to stress. The course is an international collaboration arising from the Eco2adapt EU project.
School of Computing:
Artificial Intelligence (AI) for Computer Games
Course dates: 7-11 August 2023 (1 week)
Course extent: 3-5 ECTS
Course coordinator: Ville Hautamäki (firstname.lastname@example.org)
Course description in Peppi: LT00DG54
- Basics of machine learning (one day + practical component)
What is a machine learning model? Differences between supervised, unsupervised and reinforcement learning modes of learning. Focus is on deep learning models, the basics of it will be quickly revised. Recently introduced self-supervised deep learning models will be introduced.
- AI agents (two days of lectures + practical component)
The course introduces the basics of reinforcement learning and how autonomous systems can be implemented and trained. In the course we learn how to train software agents (such as playing games, dialog systems, etc.) and how to train physical agents such as robots through simulations. Some of the lectures in this section will be given by Dr. Andrew Melnik from Bielefeld University and Dr. Anssi Kanervisto from Microsoft Research, Cambridge.
- Practice component (two days)
During the section, students implement a software agent that can play a computer game by programming (Python). An agent is a statistical model whose parameters are then learned by playing the game. There are many different models and training algorithms, and it is expected that advanced students will be able to try several of these during these two days. During the final day, students’ agents are pitted against each other in a tournament and we will recognize three best performing agents.
Introduction to Speech and Machine Learning
Course dates: 14-18 August 2023 (1 week)
Course extent: 3 ECTS
Course coordinator: Tomi Kinnunen (email@example.com)
Course description in Peppi: LT00DG43
Introductory machine learning contains self-contained introduction to elementary supervised and unsupervised learning. Evaluation of binary classifiers (e.g. type-I/II errors, ROC analysis). Introduction to modern deep learning approaches (feedforward, convolutive, recurrent). Basic idea of graph neural networks. Introductory speech processing will include speech as a carrier of linguistic information; basics of speech analysis and feature extraction, and statistical modeling. We will illustrate these ideas through application examples ranging from gender recognition, to voice biometrics (speaker recognition), speech recognition, and detection of spoofing attacks (such as audio-based deepfakes). The course contains also topics that introduce the student to research in this field, stemming from research done at the Computational Speech Group at UEF.
While no prior knowledge of speech processing or machine learning will be assumed, the participant should have sufficient programming skills. We will be working on Python code examples in the Google Colab environment.
Learning Analytics (LA)
Course dates: 7-18 August 2023 (2 weeks)
Course extent: 5 ECTS
Course coordinator: Mohammed Saqr (firstname.lastname@example.org)
Course description in Peppi: 3621691
Learning analytics (LA) is an interdisciplinary field that lies at the intersection of data science, computer science, education technology, pedagogy, and statistics. Since the field has emerged in 2011, it has exponentially grown to include a vast array of applications, and methods.
This Learning Analytics Course will provide a framework for the understanding of the field and how data has been used in education. The course will address the principles of learning analytics, discuss the theoretical background behind learning analytics and the concepts of the big data. The learning analytics main steps and procedures will be covered in detail, including data gathering, analysis, generation of insights and reporting. The main ethical and privacy issues will also be discussed.
The practical section of the course will enable attendees to practice the basics methods of analysis of educational data using real-life examples and authentic datasets. These methods include social network analysis, mixture modeling, sequence mining, process mining, predictive analytics, and machine learning.
No matter your background, you are welcome in our course. The course does not require prior programming or coding skills and uses accessible tools that can be used by everyone.
Why attend the course at University of Eastern Finland (UEF)
Our group has been among the most productive in the world in the last two years, and the most productive in Europe in 2021 and 2022. The lectures of the course have diverse analytical, methodological, pedagogical expertise.
The maximum number of participants is 30.