Learning Generative Models

(in German: Learning Generative Models )

Link:	LSF
Responsibility:	Sebastian Stober
Lecturer:	Sebastian Stober
Classes:	Lecture Learning Generative Models Exercise class Learning Generative Models
Applicability in curriculum:	- B.Sc. INF: Informatik - Wahlpflicht - B.Sc. INF: Studienprofil: Künstliche Intelligenz - B.Sc. CV: Informatik - Wahlpflicht - B.Sc. INGINF: Informatik - Wahlpflicht - B.Sc. WIF: Verstehen und Gestalten - Wahlpflicht - B.Sc. INF (bilingual): Informatik - Wahlpflicht

Abbreviation

LGM

Credit Points

Semester

Winter

Term

ab 3.

Duration

1 Semester

Language

english

Level

Bachelor

Intended learning outcomes:
Students can ..

confidently apply generative models to develop a solution for a given problem
follow recent publications on generative models and critically assess their contributions
formulate hypotheses and design & conduct experiments with generative models to validate them
document progress & design decisions for reproducibility and transparency

Content:

Training methods & architectures for generative models, in particular energy-based models (e.g. Restricted Boltzmann Machines, RBMs)
autoregressive models
variational learning and Generative Adversarial Nets (GANs)
flow-based models
diffusion models

Workload:
56 contact hours + 94h self study

Pre-examination requirements:

Type of examination:

Teaching method / lecture hours per week (SWS):

Oral exam (necessary preliminary work for admission to the examination is announced in the first week of the course)
Schein (necessary preliminary work for admission to the examination is announced in the first week of the course)

Prerequisites according to examination regulations:	Recommended prerequisites:
keine	Deep Learning für Ingenieure

Media:	Literature:
	Ian Goodfellow, Yoshua Bengio & Aaron Courville: “Deep Learning”, MIT Press, 2016.

Comments: