Avoiding local minima in multilayer network optimization by incremental training

Training a large multilayer neural network can present many difficulties due to the large number of useless stationary points. These points usually attract the minimization algorithm used during the training phase, which therefore results inefficient. Extending some results proposed in literature fo...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: De Santis, Alberto, Liuzzi, Giampaolo, Lucidi, Stefano, Tronci, Edoardo Maria
Format: Artikel
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Training a large multilayer neural network can present many difficulties due to the large number of useless stationary points. These points usually attract the minimization algorithm used during the training phase, which therefore results inefficient. Extending some results proposed in literature for shallow networks, we propose the mathematical characterization of a class of such stationary points that arise in deep neural networks training. Availing such a description, we are able to define an incremental training algorithm that avoids getting stuck in the region of attraction of these undesirable stationary points.
DOI:10.48550/arxiv.2106.06477