日本語
 
Help Privacy Policy ポリシー/免責事項
  詳細検索ブラウズ

アイテム詳細

  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

基本情報

表示: 非表示:
アイテムのパーマリンク: https://hdl.handle.net/21.11116/0000-0001-1C34-6 版のパーマリンク: https://hdl.handle.net/21.11116/0000-0001-1C35-5
資料種別: 会議論文

ファイル

表示: ファイル

作成者

表示:
非表示:
 作成者:
Theis, Lucas1, 著者           
Sohl-Dickstein, J, 著者
Bethge, Matthias1, 著者           
所属:
1Werner Reichardt Centre for Integrative Neuroscience, ou_persistent22              

内容説明

表示:
非表示:
キーワード: -
 要旨: 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.

資料詳細

表示:
非表示:
言語:
 日付: 2013-04
 出版の状態: 出版
 ページ: -
 出版情報: -
 目次: -
 査読: -
 識別子(DOI, ISBNなど): その他: TheisSB2013
 学位: -

関連イベント

表示:
非表示:
イベント名: Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012)
開催地: Lake Tahoe, NV, USA
開始日・終了日: 2012-12-03 - 2012-12-08

訴訟

表示:

Project information

表示:

出版物 1

表示:
非表示:
出版物名: Twenty-Sixth Annual Conference on Neural Information Processing Systems (NIPS 2012)
種別: 会議論文集
 著者・編者:
Bartlett, P, 編集者
Pereira, FCN, 編集者
Bottou, L, 編集者
Burges, CJC, 編集者
Weinberger, KQ, 編集者
所属:
-
出版社, 出版地: Red Hook, NY, USA : Curran
ページ: - 巻号: - 通巻号: - 開始・終了ページ: 1133 - 1141 識別子(ISBN, ISSN, DOIなど): -