MIXING SPARSITY COMPRESSION

Techniques for compressing a neural network model by mixing compression ratios (sparsity patterns) are described. The weight tensor of a neural network model is divided into weight groups. The pruning cost of compressing the weight values according to a compression ratio is determined for each weigh...

Ausführliche Beschreibung

Bibliographische Detailangaben

Hauptverfasser:	HUANG, Randy Renfu, MEYER, Paul Gilbert, PEKHIMENKO, Gennady, TAN, Xiaodan
Format:	Patent
Sprache:	eng ; fre ; ger
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!