A Limitation of Gradient Descent Learning

Over decades, gradient descent has been applied to develop learning algorithm to train a neural network (NN). In this brief, a limitation of applying such algorithm to train an NN with persistent weight noise is revealed. Let V({\mathbf w}) be the performance measure of an ideal NN. V({\mathbf w}...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transaction on neural networks and learning systems 2020-06, Vol.31 (6), p.2227-2232
Hauptverfasser:	Sum, John, Leung, Chi-Sing, Ho, Kevin
Format:	Artikel
Sprache:	eng
Schlagworte:	Additive weight noise Additives Algorithms Artificial neural networks Computational modeling Computer simulation gradient descent algorithms Handwriting recognition Hardware Learning Learning curves Learning systems Linear programming Machine learning MNIST multiplicative weight noise Neural networks Noise Noise measurement Regression analysis Weight
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!