Patent · US Active

Reducing the size of a neural network through reduction of the weight matrices

US10127495B1 · kind B1 · utility

17Cited by
0References
18Claims
0Family size

Inventors

Key dates

Filing dateApr 14, 2017
Grant dateNov 13, 2018
Priority date
Expiry dateJun 11, 2037

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/063
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems and methods for reducing the size of deep neural networks are disclosed. In an embodiment, a server computer stores a plurality of training datasets, each of which comprise a plurality of training input matrices and a plurality of corresponding outputs. The server computer initiates training of a deep neural network using the plurality of training input matrices, a weight matrix, and the plurality of corresponding outputs. While the training of the deep neural network is being performed, the server computer identifies one or more weight values of the weight matrix for removal. The server computer removes the one or more weight values from the weight matrix to generate a reduced weight matrix. The server computer then stores the reduced weight matrix with the deep neural network.

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