English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse
  1. Item Summary / 
  2. View item

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  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

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-000A-E35A-1 Version Permalink: https://hdl.handle.net/21.11116/0000-000A-E35B-0
Genre: Talk

Files

show Files

Creators

show
hide
 Creators:
Solopchuk, O1, Author           
Affiliations:
1Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_3017468              

Content

show
hide
Free keywords: -
 Abstract: 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.

Details

show
hide
Language(s):
 Dates: 2022-07
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: Freie Universität, Department of Education and Psychology, Center for Cognitive Neuroscience Berlin
Place of Event: Berlin, Germany
Start-/End Date: 2022-07-18
Invited: Yes

Legal Case

show

Project information

show

Source

show