Universität Wien
Warning! The directory is not yet complete and will be amended until the beginning of the term.

301117 SE Elements of Machine Learning (2025S)

3.00 ECTS (2.00 SWS), SPL 30 - Biologie
Continuous assessment of course work

Fr 07.03. 13:15-14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1

Details

max. 20 participants
Language: English

Lecturers

    Classes (iCal) - next class is marked with N

    • Friday 14.03. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 21.03. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 28.03. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 04.04. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 11.04. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 02.05. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 09.05. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 16.05. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 23.05. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 30.05. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 06.06. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 13.06. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 20.06. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1
    • Friday 27.06. 13:15 - 14:45 Seminarraum 1.4, Biologie Djerassiplatz 1, 1.013, Ebene 1

    Information

    Aims, contents and method of the course

    Anyone reading this text has probably heard of or even used ChatGPT, and some have even found it rewarding. This course is not about ChatGPT, but explores the theoretical foundations of Machine Learning. We will explore basic properties of statistical models, and gain insight into the beating heart of some machine-learning algorithms. While our tools will be mathematical, the goal is not to manipulate numbers and other fancy symbols, but to gain intuition about statistical learning and the clever methods people found to drive it.

    We will start with basic concepts from probability theory, such as statistical independence, expectation and variance among others. The goal is to make sure we are confident in the basic building blocks that will be used throughout the course. We will then cover abstract properties like model Generalizability, VC-dimension, Bias-Variance tradeoffs, mixing them into applied algorithms like linear and logistic regression, perceptrons, and eventually neural networks to name a few.

    After completing the course, students will be able to apply advanced statistical tools and follow new statistical learning methods with confidence. In other words, you will be the life of every party with your incredible insights into the amazing world of machine learning theory and applications.

    Assessment and permitted materials

    2 quizzes and 2 homework assignments.
    Homeworks contribute 50% to the final grade and quizzes contribute 50%.
    A passing grade is >50% of combined assessments.

    Minimum requirements and assessment criteria

    Minimum requirements:
    While the course is mathematical, I will try to be as self-contained as possible, and there are no hard minimal requirements beyond high-school level math.

    Assessment criteria:
    Homework will involve working through mathematical problems related to course material. These will not involve a lot of elaborate algebra, but will require a deep understanding of the material.
    Quizzes will be about concepts, and will not involve solving math problems.

    Examination topics

    Students will be tested on their understanding of concepts learned during the course.
    These will include the motivating ideas behind different learning algorithms, as well as theoretical analyses of learning-related probabilistic models and algorithms

    Reading list

    None. All material will be covered in class during the lectures.
    Extra reading for those who are interested will be provided in Moodle

    Association in the course directory

    MMEI II-2.2

    Last modified: Fr 10.01.2025 00:02