Deutsch
 
Hilfe Datenschutzhinweis Impressum
  DetailsucheBrowse

Datensatz

DATENSATZ AKTIONENEXPORT
  Training sparse natural image models with a fast Gibbs sampler of an extended state space

Theis, L., Sohl-Dickstein, J., & Bethge, M. (2013). Training sparse natural image models with a fast Gibbs sampler of an extended state space. In P. Bartlett, F. Pereira, L. Bottou, C. Burges, & K. Weinberger (Eds.), Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012) (pp. 1133-1141). Red Hook, NY, USA: Curran.

Item is

Basisdaten

einblenden: ausblenden:
Genre: Konferenzbeitrag

Urheber

einblenden:
ausblenden:
 Urheber:
Theis, Lucas1, Autor           
Sohl-Dickstein, J, Autor
Bethge, Matthias1, Autor           
Affiliations:
1Werner Reichardt Centre for Integrative Neuroscience, ou_persistent22              

Inhalt

einblenden:
ausblenden:
Schlagwörter: -
 Zusammenfassung: We present a new learning strategy based on an efficient blocked Gibbs sampler for sparse overcomplete linear models. Particular emphasis is placed on statistical image modeling, where overcomplete models have played an important role in discovering sparse representations. Our Gibbs sampler is faster than general purpose sampling schemes while also requiring no tuning as it is free of parameters. Using the Gibbs sampler and a persistent variant of expectation maximization, we are able to extract highly sparse distributions over latent sources from data. When applied to natural images, our algorithm learns source distributions which resemble spike-and-slab distributions. We evaluate the likelihood and quantitatively compare the performance of the overcomplete linear model to its complete counterpart as well as a product of experts model, which represents another overcomplete generalization of the complete linear model. In contrast to previous claims, we find that overcomplete representations lead to significant improvements, but that the overcomplete linear model still underperforms other models.

Details

einblenden:
ausblenden:
Sprache(n):
 Datum: 2013-04
 Publikationsstatus: Erschienen
 Seiten: -
 Ort, Verlag, Ausgabe: -
 Inhaltsverzeichnis: -
 Art der Begutachtung: -
 Identifikatoren: Anderer: TheisSB2013
 Art des Abschluß: -

Veranstaltung

einblenden:
ausblenden:
Titel: Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012)
Veranstaltungsort: Lake Tahoe, NV, USA
Start-/Enddatum: 2012-12-03 - 2012-12-08

Entscheidung

einblenden:

Projektinformation

einblenden:

Quelle 1

einblenden:
ausblenden:
Titel: Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012)
Genre der Quelle: Konferenzband
 Urheber:
Bartlett, P, Herausgeber
Pereira, FCN, Herausgeber
Bottou, L, Herausgeber
Burges, CJC, Herausgeber
Weinberger, KQ, Herausgeber
Affiliations:
-
Ort, Verlag, Ausgabe: Red Hook, NY, USA : Curran
Seiten: - Band / Heft: - Artikelnummer: - Start- / Endseite: 1133 - 1141 Identifikator: -