Patent · US Active

Compression of fully connected / recurrent layers of deep network(s) through enforcing spatial locality to weight matrices and effecting frequency compression

US11977974B2 · kind B2 · utility

0Cited by
3References
12Claims
0Family size

Assignee

Inventors

Key dates

Filing dateNov 30, 2017
Grant dateMay 7, 2024
Priority date
Expiry dateMay 7, 2041

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A system, having a memory that stores computer executable components, and a processor that executes the computer executable components, reduces data size in connection with training a neural network by exploiting spatial locality to weight matrices and effecting frequency transformation and compression. A receiving component receives neural network data in the form of a compressed frequency-domain weight matrix. A segmentation component segments the initial weight matrix into original sub-components, wherein respective original sub-components have spatial weights. A sampling component applies a generalized weight distribution to the respective original sub-components to generate respective normalized sub-components. A transform component applies a transform to the respective normalized sub-components. A cropping component crops high-frequency weights of the respective transformed normalized sub-components to yield a set of low-frequency normalized sub-components to generate a compressed representation of the original sub-components.

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