English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Learning Multiple Feature Representations from Natural Image Sequences

Einhäuser, W., Kayser, C., Kording, K., & König, P. (2002). Learning Multiple Feature Representations from Natural Image Sequences. In J. Dorronsoro (Ed.), Artificial Neural Networks: ICANN 2002: International Conference Madrid, Spain, August 28–30, 2002 (pp. 21-26). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-E072-5 Version Permalink: https://hdl.handle.net/21.11116/0000-0005-8D51-1
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007%2F3-540-46084-5_4.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Einhäuser, W, Author
Kayser, C1, Author           
Kording, KP, Author
König, P, Author
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: Hierarchical neural networks require the parallel extraction of multiple features. This raises the question how a subpopulation of cells can become specific to one feature and invariant to another, while a different subpopulation becomes invariant to the first but specific to the second feature. Using a colour image sequence recorded by a camera mounted to a cat’s head, we train a population of neurons to achieve optimally stable responses. We find that colour sensitive cells emerge. Adding the additional objective of decorrelating the neurons’ outputs leads a subpopulation to develop achromatic receptive fields. The colour sensitive cells tend to be non-oriented, while the achromatic cells are orientation-tuned, in accordance with physiological findings. The proposed objective thus successfully separates cells which are specific for orientation and invariant to colour from orientation invariant colour cells.

Details

show
hide
Language(s):
 Dates: 2002-01
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/3-540-46084-5_4
BibTex Citekey: 2959
 Degree: -

Event

show
hide
Title: International Conference on Artificial Neural Networks (ICANN 2002)
Place of Event: Madrid, Spain
Start-/End Date: 2002-08-28 - 2002-08-30

Legal Case

show

Project information

show

Source 1

show
hide
Title: Artificial Neural Networks: ICANN 2002: International Conference Madrid, Spain, August 28–30, 2002
Source Genre: Proceedings
 Creator(s):
Dorronsoro, JR, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 21 - 26 Identifier: ISBN: 978-3-540-44074-1

Source 2

show
hide
Title: Lecture Notes in Computer Science
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 2415 Sequence Number: - Start / End Page: - Identifier: -