Endre søk
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf
Banach Wasserstein GAN
KTH, Skolan för teknikvetenskap (SCI), Matematik (Inst.), Matematik (Avd.).ORCID-id: 0000-0001-9928-3407
Univ Cambridge, Dept Appl Math & Theoret Phys, Cambridge, England..
2018 (engelsk)Inngår i: Advances in Neural Information Processing Systems 31 (NIPS 2018) / [ed] Bengio, S Wallach, H Larochelle, H Grauman, K CesaBianchi, N Garnett, R, Neural Information Processing Systems (NIPS) , 2018Konferansepaper, Publicerat paper (Fagfellevurdert)
Abstract [en]

Wasserstein Generative Adversarial Networks (WGANs) can be used to generate realistic samples from complicated image distributions. The Wasserstein metric used in WGANs is based on a notion of distance between individual images, which induces a notion of distance between probability distributions of images. So far the community has considered l(2) as the underlying distance. We generalize the theory of WGAN with gradient penalty to Banach spaces, allowing practitioners to select the features to emphasize in the generator. We further discuss the effect of some particular choices of underlying norms, focusing on Sobolev norms. Finally, we demonstrate a boost in performance for an appropriate choice of norm on CIFAR-10 and CelebA.

sted, utgiver, år, opplag, sider
Neural Information Processing Systems (NIPS) , 2018.
Serie
Advances in Neural Information Processing Systems, ISSN 1049-5258 ; 31
HSV kategori
Identifikatorer
URN: urn:nbn:se:kth:diva-249915ISI: 000461852001031OAI: oai:DiVA.org:kth-249915DiVA, id: diva2:1307316
Konferanse
32nd Conference on Neural Information Processing Systems (NIPS), DEC 02-08, 2018, Montreal, Canada
Merknad

QC 20190426

Tilgjengelig fra: 2019-04-26 Laget: 2019-04-26 Sist oppdatert: 2019-10-18bibliografisk kontrollert
Inngår i avhandling
1. Data-driven Methods in Inverse Problems
Åpne denne publikasjonen i ny fane eller vindu >>Data-driven Methods in Inverse Problems
2019 (engelsk)Doktoravhandling, med artikler (Annet vitenskapelig)
Abstract [en]

In this thesis on data-driven methods in inverse problems we introduce several new methods to solve inverse problems using recent advancements in machine learning and specifically deep learning. The main goal has been to develop practically applicable methods, scalable to medical applications and with the ability to handle all the complexities associated with them.

In total, the thesis contains six papers. Some of them are focused on more theoretical questions such as characterizing the optimal solutions of reconstruction schemes or extending current methods to new domains, while others have focused on practical applicability. A significant portion of the papers also aim to bringing knowledge from the machine learning community into the imaging community, with considerable effort spent on translating many of the concepts. The papers have been published in a range of venues: machine learning, medical imaging and inverse problems.

The first two papers contribute to a class of methods now called learned iterative reconstruction where we introduce two ways of combining classical model driven reconstruction methods with deep neural networks. The next two papers look forward, aiming to address the question of "what do we want?" by proposing two very different but novel loss functions for training neural networks in inverse problems. The final papers dwelve into the statistical side, one gives a generalization of a class of deep generative models to Banach spaces while the next introduces two ways in which such methods can be used to perform Bayesian inversion at scale.

sted, utgiver, år, opplag, sider
Stockholm: KTH Royal Institute of Technology, 2019. s. 196
Serie
TRITA-SCI-FOU ; 2019;49
Emneord
Inverse Problems, Machine Learning, Tomography
HSV kategori
Identifikatorer
urn:nbn:se:kth:diva-262727 (URN)978-91-7873-334-7 (ISBN)
Disputas
2019-10-31, F3, Lindstedtsvägen26, KTH, Stockholm, 14:00 (engelsk)
Opponent
Veileder
Forskningsfinansiär
Swedish Foundation for Strategic Research
Tilgjengelig fra: 2019-10-21 Laget: 2019-10-18 Sist oppdatert: 2019-10-21bibliografisk kontrollert

Open Access i DiVA

Fulltekst mangler i DiVA

Personposter BETA

Adler, Jonas

Søk i DiVA

Av forfatter/redaktør
Adler, Jonas
Av organisasjonen

Søk utenfor DiVA

GoogleGoogle Scholar

urn-nbn

Altmetric

urn-nbn
Totalt: 397 treff
RefereraExporteraLink to record
Permanent link

Direct link
Referera
Referensformat
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Annet format
Fler format
Språk
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Annet språk
Fler språk
Utmatningsformat
  • html
  • text
  • asciidoc
  • rtf