TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING

TRAINING TRANSFER-FOCUSED MODELS FOR DEEP LEARNING

Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be de...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Watson, Patrick, Bhattacharjee, Bishwaranjan, Kender, John Ronald, Huo, Siyu, Glass, Michael Robert, Codella, Noel Christopher, Dube, Parijat, Belgodere, Brian Michael, Hill, Matthew Leon
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Whether to train a new neural network model can be determined based on similarity estimates between a sample data set and a plurality of source data sets associated with a plurality of prior-trained neural network models. A cluster among the plurality of prior-trained neural network models can be determined. A set of training data based on the cluster can be determined. The new neural network model can be trained based on the set of training data.