Wird geladen...

Dynamics of stochastic gradient descent for two-layer neural networks in the teacher–student setup

Deep neural networks achieve stellar generalisation even when they have enough parameters to easily fit all their training data. We study this phenomenon by analysing the dynamics and the performance of over-parameterised two-layer neural networks in the teacher–student setup, where one network, the...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:J Stat Mech
Hauptverfasser: Goldt, Sebastian, Advani, Madhu S, Saxe, Andrew M, Krzakala, Florent, Zdeborová, Lenka
Format: Artigo
Sprache:Inglês
Veröffentlicht: IOP Publishing and SISSA 2020
Schlagworte:
Online Zugang:https://ncbi.nlm.nih.gov/pmc/articles/PMC8252911/
https://ncbi.nlm.nih.gov/pubmed/34262607
https://ncbi.nlm.nih.govhttp://dx.doi.org/10.1088/1742-5468/abc61e
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!