CS-E4891 - Deep Generative Models D, Lecture, 24.2.2025-6.6.2025

Please note! Course description is confirmed for two academic years, which means that in general, e.g. Learning outcomes, assessment methods and key content stays unchanged. However, via course syllabus, it is possible to specify or change the course execution in each realization of the course, such as how the contact sessions are organized, assessment methods weighted or materials used.

LEARNING OUTCOMES

Students will learn the general principles of deep generative modeling and uncertainty quantification as well as the current deep generative modeling methods. After the course, students will be able to apply the methods to real-world data sets and study the topic further.

Credits: 5

Schedule: 24.02.2025 - 06.06.2025

Teacher in charge (valid for whole curriculum period):

Teacher in charge (applies in this implementation): Harri Lähdesmäki, Lauri Juvela

Contact information for the course (applies in this implementation):

CEFR level (valid for whole curriculum period):

Language of instruction and studies (applies in this implementation):

Teaching language: English. Languages of study attainment: English

CONTENT, ASSESSMENT AND WORKLOAD

Content

  • valid for whole curriculum period:

    Fundamental and current topics of generative modeling and uncertainty quantification. Both methodological and implementing aspects are part of the course contents. 

    Topics include

    • Monte Carlo methods
    • Divergence measures
    • Variational inference and autoencoders
    • Deep state-space models
    • Diffusion models
    • Generative Adversarial Networks (GANs)

Assessment Methods and Criteria

  • valid for whole curriculum period:

    Exam, exercises and assignments.

Workload

  • valid for whole curriculum period:

    1 lecture per week (1h 30 min total each), one exercise session per week (1 h 30 min total each), and the rest for studying the course material, doing exercises and assignments, and preparing for an exam.

DETAILS

Study Material

  • valid for whole curriculum period:

    Lecture notes and book(s). 

    Details will be specified in MyCourses at the beginning of the course.

Substitutes for Courses
Prerequisites
SDG: Sustainable Development Goals

    3 Good Health and Well-being

    5 Gender Equality

    9 Industry, Innovation and Infrastructure

FURTHER INFORMATION

Further Information

  • valid for whole curriculum period:

    Teaching Language: English

    Teaching Period: 2024-2025 Spring IV - V
    2025-2026 Spring IV - V

Rules of Conduct - Students´ Rights and Responsibilities (in force from 1 August 2020)

Aalto University Code of Academic Integrity and Handling Violations Thereof