Deep Kronecker neural networks: A general framework for neural networks with adaptive activation functions

Here we propose a new type of neural networks, Kronecker neural networks (KNNs), that form a general framework for neural networks with adaptive activation functions. KNNs employ the Kronecker product, which provides an efficient way of constructing a very wide network while keeping the number of pa...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Neurocomputing (Amsterdam) 2021-10, Vol.468 (C)
Hauptverfasser:	Jagtap, Ameya D., Shin, Yeonjong, Kawaguchi, Kenji, Karniadakis, George Em
Format:	Artikel
Sprache:	eng
Schlagworte:	deep learning benchmarks deep neural networks gradient flow dynamics Kronecker product MATHEMATICS AND COMPUTING physics-informed neural networks rowdy activation functions
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!