Connection weight changes and learning dynamics in models of neural networks
- Standort
-
Deutsche Nationalbibliothek Frankfurt am Main
- Umfang
-
Online-Ressource
- Sprache
-
Englisch
- Anmerkungen
-
In: https://doi.org/10.1103/PhysRevLett.125.088103
In: https://doi.org/10.1101/2021.10.04.463055
In: https://doi.org/10.1073/pnas.2023832118
In: https://doi.org/10.1523/JNEUROSCI.2594-18.2019
Bonn, Rheinische Friedrich-Wilhelms-Universität, Dissertation, 2022
- Schlagwort
-
Nervennetz
Neuronales Netz
Modell
Maschinelles Lernen
Pulsverarbeitendes neuronales Netz
Nervenzelle
Hirnfunktion
- Ereignis
-
Veröffentlichung
- (wo)
-
Bonn
- (wer)
-
Universitäts- und Landesbibliothek Bonn
- (wann)
-
2022
- Urheber
- Beteiligte Personen und Organisationen
-
Memmesheimer, Raoul-Martin
Meißner, Ulf-G.
- Handle
-
20.500.11811/9787
- URN
-
urn:nbn:de:hbz:5-66272
- Rechteinformation
-
Der Zugriff auf das Objekt ist unbeschränkt möglich.
- Letzte Aktualisierung
-
15.08.2025, 07:28 MESZ
Datenpartner
Dieses Objekt wird bereitgestellt von:
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Deutsche Nationalbibliothek. Bei Fragen zum Objekt wenden Sie sich bitte an den Datenpartner.
Beteiligte
- Klos, Christian
- Memmesheimer, Raoul-Martin
- Meißner, Ulf-G.
- Universitäts- und Landesbibliothek Bonn
Entstanden
- 2022
Ähnliche Objekte (12)
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Neural Networks with Sequentially Semiseparable Weight Matrices
Weight statistics controls dynamics in recurrent neural networks
Learning Weight Signed Network Embedding with Graph Neural Networks
Optimised weight programming for analogue memory-based deep neural networks
Percolation in weight-dependent random connection models
A novel metaheuristic population algorithm for optimising the connection weights of neural networks
Implementation of Optimal Connection Networks
Generalization at Retrieval Using Associative Networks with Transient Weight Changes
Why neural networks? History of neural networks
Explanations for neural networks by neural networks
Parental weight changes as key predictors of child weight changes
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Neural Networks with Sequentially Semiseparable Weight Matrices
Weight statistics controls dynamics in recurrent neural networks
Learning Weight Signed Network Embedding with Graph Neural Networks
Optimised weight programming for analogue memory-based deep neural networks
Percolation in weight-dependent random connection models
A novel metaheuristic population algorithm for optimising the connection weights of neural networks
Implementation of Optimal Connection Networks
Generalization at Retrieval Using Associative Networks with Transient Weight Changes
Why neural networks? History of neural networks
Explanations for neural networks by neural networks
Parental weight changes as key predictors of child weight changes
An analysis of weight initialization methods in connection with different activation functions forfeedforward neural networks
Neural Networks with Sequentially Semiseparable Weight Matrices
Weight statistics controls dynamics in recurrent neural networks
Learning Weight Signed Network Embedding with Graph Neural Networks
Optimised weight programming for analogue memory-based deep neural networks
Percolation in weight-dependent random connection models
A novel metaheuristic population algorithm for optimising the connection weights of neural networks
Implementation of Optimal Connection Networks
Generalization at Retrieval Using Associative Networks with Transient Weight Changes
Why neural networks? History of neural networks
Explanations for neural networks by neural networks