Status: Bibliographieeintrag
Standort: ---
Exemplare:
---
| Online-Ressource |
Verfasst von: | Sorrenson, Peter [VerfasserIn] ![i](/opacicon/information2.png) |
| Rother, Carsten [VerfasserIn] ![i](/opacicon/information2.png) |
| Köthe, Ullrich [VerfasserIn] ![i](/opacicon/information2.png) |
Titel: | Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN) |
Verf.angabe: | Peter Sorrenson, Carsten Rother, Ullrich Köthe |
E-Jahr: | 2020 |
Jahr: | 14 Jan 2020 |
Umfang: | 23 S. |
Fussnoten: | Gesehen am 19.07.2022 |
Titel Quelle: | Enthalten in: De.arxiv.org |
Ort Quelle: | [S.l.] : Arxiv.org, 1991 |
Jahr Quelle: | 2020 |
Band/Heft Quelle: | (2020), Artikel-ID 2001.04872, Seite 1-23 |
Abstract: | A central question of representation learning asks under which conditions it is possible to reconstruct the true latent variables of an arbitrarily complex generative process. Recent breakthrough work by Khemakhem et al. (2019) on nonlinear ICA has answered this question for a broad class of conditional generative processes. We extend this important result in a direction relevant for application to real-world data. First, we generalize the theory to the case of unknown intrinsic problem dimension and prove that in some special (but not very restrictive) cases, informative latent variables will be automatically separated from noise by an estimating model. Furthermore, the recovered informative latent variables will be in one-to-one correspondence with the true latent variables of the generating process, up to a trivial component-wise transformation. Second, we introduce a modification of the RealNVP invertible neural network architecture (Dinh et al. (2016)) which is particularly suitable for this type of problem: the General Incompressible-flow Network (GIN). Experiments on artificial data and EMNIST demonstrate that theoretical predictions are indeed verified in practice. In particular, we provide a detailed set of exactly 22 informative latent variables extracted from EMNIST. |
DOI: | doi:10.48550/arXiv.2001.04872 |
URL: | Bitte beachten Sie: Dies ist ein Bibliographieeintrag. Ein Volltextzugriff für Mitglieder der Universität besteht hier nur, falls für die entsprechende Zeitschrift/den entsprechenden Sammelband ein Abonnement besteht oder es sich um einen OpenAccess-Titel handelt.
Volltext ; Verlag: https://doi.org/10.48550/arXiv.2001.04872 |
| Volltext: http://arxiv.org/abs/2001.04872 |
| DOI: https://doi.org/10.48550/arXiv.2001.04872 |
Datenträger: | Online-Ressource |
Sprache: | eng |
Sach-SW: | Computer Science - Machine Learning |
| Statistics - Machine Learning |
K10plus-PPN: | 1810850444 |
Verknüpfungen: | → Sammelwerk |
Disentanglement by nonlinear ICA with General Incompressible-flow Networks (GIN) / Sorrenson, Peter [VerfasserIn]; 14 Jan 2020 (Online-Ressource)
68944096