Patent · US Active

Deep neural network partitioning on servers

US10452971B2 · kind B2 · utility

7Cited by
6References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJun 29, 2015
Grant dateOct 22, 2019
Priority date
Expiry dateJul 25, 2037

Classification

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

Abstract

A method is provided for implementing a deep neural network on a server component that includes a host component including a CPU and a hardware acceleration component coupled to the host component. The deep neural network includes a plurality of layers. The method includes partitioning the deep neural network into a first segment and a second segment, the first segment including a first subset of the plurality of layers, the second segment including a second subset of the plurality of layers, configuring the host component to implement the first segment, and configuring the hardware acceleration component to implement the second segment.

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