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

  Active sensing with artificial neural networks

Solopchuk, O. (2022). Active sensing with artificial neural networks. Talk presented at Freie Universität, Department of Education and Psychology, Center for Cognitive Neuroscience Berlin. Berlin, Germany. 2022-07-18.

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/21.11116/0000-000A-E35A-1 版のパーマリンク: https://hdl.handle.net/21.11116/0000-000A-E35B-0
資料種別: 講演

ファイル

表示: ファイル

作成者

表示:
非表示:
 作成者:
Solopchuk, O1, 著者           
所属:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              

内容説明

表示:
非表示:
キーワード: -
 要旨: The fitness of behaving agents depends on their knowledge of the environment, which demands efficient exploration strategies. Active sensing formalizes exploration as reduction of uncertainty about the current state of the environment. Despite strong theoretical justifications, active sensing has had limited applicability due to difficulty in estimating information gain. Here we address this issue by proposing a linear approximation to information gain and by implementing efficient gradient-based action selection within an artificial neural network setting. We compare information gain estimation with state of the art, and validate our model on an active sensing task based on MNIST dataset. We also propose an approximation that exploits the amortized inference network, and performs equally well in certain contexts.

資料詳細

表示:
非表示:
言語:
 日付: 2022-07
 出版の状態: オンラインで出版済み
 ページ: -
 出版情報: -
 目次: -
 査読: -
 識別子(DOI, ISBNなど): -
 学位: -

関連イベント

表示:
非表示:
イベント名: Freie Universität, Department of Education and Psychology, Center for Cognitive Neuroscience Berlin
開催地: Berlin, Germany
開始日・終了日: 2022-07-18
招待講演: 招待

訴訟

表示:

Project information

表示:

出版物

表示: