Seminar: Blockseminar: Neural ODE and Generative Modelling (Master Seminar) - Details

Seminar: Blockseminar: Neural ODE and Generative Modelling (Master Seminar) - Details

Close message box
You are not logged into Stud.IP.

General information

Course name Seminar: Blockseminar: Neural ODE and Generative Modelling (Master Seminar)
Course number MTH-1360; MTH-1410
Semester WS 2024/25
Current number of participants 3
expected number of participants 15
Home institute Mathematische Bildverarbeitung
Courses type Seminar in category Teaching
Type/Form Blockseminar
Veranstaltung findet in Präsenz statt / hat Präsenz-Bestandteile Yes
Hauptunterrichtssprache englisch
Weitere Unterrichtssprache(n) Deutsch

Rooms and times

No room preference

Module assignments

Comment/Description

Score-based generative models have demonstrated state-of-the-art performance in numerous applications in recent years. The central concept behind these models involves the gradual injection of noise into the training data, followed by learning the reverse process to generate new samples. The training and sampling procedures can be conducted independently. The learning phase is facilitated by noise-conditional score networks, while sampling can be accomplished through various methods, including Langevin Monte Carlo approaches, stochastic differential equations, ordinary differential equations, and various combinations.

This seminar will overview generative models and common architectures, comparing different training objectives and sampling methods. We will examine normalizing flows, score matching, and Langevin dynamics. Additionally, we will discuss the use of stochastic differential equations (SDEs) in score-based models and conclude with comparisons to other diffusion models and potential enhancements in sample generation.