Citation link: http://dx.doi.org/10.25819/ubsi/10472
Files in This Item:
File Description SizeFormat
Dissertation_Saseendran_Amrutha.pdf13.42 MBAdobe PDFThumbnail
View/Open
Dokument Type: Doctoral Thesis
metadata.dc.title: Optimizing the latent space of deep generative models
Other Titles: Optimierung des latenten Raums von tiefen generativen Modellen
Authors: Saseendran, Amrutha 
Institute: Department Elektrotechnik - Informatik 
Free keywords: Generative models, Representation learning, Generative Adversarial Network, Variational Autoencoder, Adversarial robustness, Generative Modelle, Repräsentatives Lernen, Generatives Adversariales Netzwerk, Variierender Autoencoder, Adversarielle Robustheit
Dewey Decimal Classification: 004 Informatik
GHBS-Clases: TVUC
TVVC
TUH
Issue Date: 2023
Publish Date: 2024
Abstract: 
Deep generative models are powerful machine learning models used to model high-dimensional complex data distributions. The rich and semantically expressive latent representations learned by these models are used for various downstream applications in computer vision and natural language processing. It is evident that the effectiveness of the generative techniques highly depends on the quality of t...

Tiefe generative Modelle sind leistungsstarke maschinelle Lernmodelle, die zur Modellierung hochdimensionaler komplexer Datenverteilungen verwendet werden. Die reichhaltigen und semantisch aussagekräftigen latenten Repräsentationen, die von diesen Modellen erlernt werden, werden für verschiedene Anwendungen in der Computer Vision und der Verarbeitung natürlicher Sprache verwendet. Es ist offensich...
DOI: http://dx.doi.org/10.25819/ubsi/10472
URN: urn:nbn:de:hbz:467-26841
URI: https://dspace.ub.uni-siegen.de/handle/ubsi/2684
Appears in Collections:Hochschulschriften

This item is protected by original copyright

Show full item record

Page view(s)

406
checked on Apr 5, 2025

Download(s)

120
checked on Apr 5, 2025

Google ScholarTM

Check