Sparsely Activated Networks

Previous literature on unsupervised learning focused on designing structural priors with the aim of learning meaningful features. However, this was done without considering the description length of the learned representations, which is a direct and unbiased measure of the model complexity. In this...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2021-03, Vol.32 (3), p.1304-1313
Hauptverfasser:	Bizopoulos, Paschalis, Koutsouris, Dimitrios
Format:	Artikel
Sprache:	eng
Schlagworte:	Artificial neural networks autoencoders Biological neural networks Compression Computational modeling Data models Epilepsy Kernel Kernels Measurement Model accuracy Neurons Representations sparsity Unsupervised learning
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!