English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Tailored ensembles of neural networks optimize sensitivity to stimulus statistics

Zierenberg, J., Wilting, J., Priesemann, V., & Levina, A. (2021). Tailored ensembles of neural networks optimize sensitivity to stimulus statistics. Poster presented at DPG-Frühjahrstagungen 2021 BP-CPP-DY-SOE.

Item is

Files

show Files

Creators

show
hide
 Creators:
Zierenberg, J, Author
Wilting, J, Author
Priesemann, V, Author
Levina, A1, 2, Author              
Affiliations:
1Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              
2Department of Computational Neuroscience, Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_3017468              

Content

show
hide
Free keywords: -
 Abstract: The capability of a living organism to process stimuli with nontrivial intensity distributions cannot be explained by the proficiency of a single neural network. Moreover, it is not sufficient to maximize the dynamic range of the neural response; it is also necessary to tune the response to the intervals of stimulus intensities that should be reliably discriminated. We derive a class of neural networks where these intervals can be tuned to the desired interval. This allows us to tailor ensembles of networks optimized for arbitrary stimulus intensity distributions. We discuss potential applications in machine learning.

Details

show
hide
Language(s):
 Dates: 2021-03
 Publication Status: Published online
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: -
 Degree: -

Event

show
hide
Title: DPG-Frühjahrstagungen 2021 BP-CPP-DY-SOE
Place of Event: -
Start-/End Date: 2021-03-22 - 2021-03-24

Legal Case

show

Project information

show

Source 1

show
hide
Title: Virtual DPG Spring Meeting 2021 of the Divisions Biological Physics, Chemical and Polymer Physics, Dynamics and Statistical Physics, Physics of Socio-economic Systems
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: BP 24.30 Start / End Page: 47 Identifier: -