A novel feature-scrambling approach reveals the capacity of convolutional neural networks to learn spatial relations

to related objects

Location
Deutsche Nationalbibliothek Frankfurt am Main
Extent
Online-Ressource
Language
Englisch

Bibliographic citation
In: Neural networks, 167.2023, S. 400-414

Event
Veröffentlichung
(where)
Frankfurt am Main
(who)
Universitätsbibliothek Johann Christian Senckenberg
(when)
2023
Creator
Farahat, Amr
Effenberger, Felix
Vinck, Martin

DOI
10.1016/j.neunet.2023.08.021
URN
urn:nbn:de:hebis:30:3-762715
Rights
Der Zugriff auf das Objekt ist unbeschränkt möglich.
Last update
14.08.2025, 11:03 AM CEST

Data provider

This object is provided by:
Deutsche Nationalbibliothek. If you have any questions about the object, please contact the data provider.
Show original at data provider

Associated

  • Farahat, Amr
  • Effenberger, Felix
  • Vinck, Martin
  • Universitätsbibliothek Johann Christian Senckenberg

Time of origin

  • 2023

Other Objects (12)

Learn class hierarchy using convolutional neural networks

Learn class hierarchy using convolutional neural networks

Scrambling and barriers

Aufsatzsammlung

Scrambling and barriers

Scrambling and incorporation

Scrambling and incorporation

Firewalls vs. scrambling

Firewalls vs. scrambling

Scrambling and interfaces

Scrambling and interfaces

Scrambling and quantum teleportation

Scrambling and quantum teleportation

Scrambling with conservation laws

Scrambling with conservation laws

Scrambling in Yang-Mills

Scrambling in Yang-Mills

Scrambling techniques for digital transmission

Scrambling techniques for digital transmission

Scrambling techniques for digital transmission

Scrambling techniques for digital transmission

Towards the fast scrambling conjecture

Towards the fast scrambling conjecture

Scrambling and entangling spinning particles

Scrambling and entangling spinning particles

Related objects