Patent · US Active

Method and apparatus for reducing the parameter density of a deep neural network (DNN)

US11887001B2 · kind B2 · utility

0Cited by
0References
21Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 26, 2016
Grant dateJan 30, 2024
Priority date
Expiry dateMar 19, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/044
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

An apparatus and method are described for reducing the parameter density of a deep neural network (DNN). A layer-wise pruning module to prune a specified set of parameters from each layer of a reference dense neural network model to generate a second neural network model having a relatively higher sparsity rate than the reference neural network model; a retraining module to retrain the second neural network model in accordance with a set of training data to generate a retrained second neural network model; and the retraining module to output the retrained second neural network model as a final neural network model if a target sparsity rate has been reached or to provide the retrained second neural network model to the layer-wise pruning model for additional pruning if the target sparsity rate has not been reached.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.