MACHINE LEARNING DEVICE, INFERENCE DEVICE, MACHINE LEARNING METHOD, AND MACHINE LEARNING PROGRAM

An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model traine...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	KIDA Shingo, TAKEHARA Hideki, YANG Yincheng
Format:	Patent
Sprache:	eng ; fre ; ger
Schlagworte:	CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Beschreibung
Zusammenfassung:	An initialization rate determination unit (22) determines, in accordance with a depth of a layer in a neural network model, a first initialization rate for initializing weights in the neural network model on a first task. A machine learning execution unit (24) generates a neural network model trained on a first task by training on the first task by machine learning. An initialization unit (26) initializes weights in the neural network model trained on the first task, based on the first initialization rate, to generate an initialized neural network model trained on the first task, the initialized neural network trained on the first task being used in a second task.