Patent · US Active

Compiling code for a machine learning model for execution on a specialized processor

US11175898B2 · kind B2 · utility

0Cited by
1References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 25, 2019
Grant dateNov 16, 2021
Priority date
Expiry dateSep 25, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/048
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

The subject technology receives a neural network model in a model format, the model format including information for a set of layers of the neural network model, each layer of the set of layers including a set of respective operations. The subject technology generates neural network (NN) code from the neural network model, the NN code being in a programming language distinct from the model format, and the NN code comprising a respective memory allocation for each respective layer of the set of layers of the neural network model, where the generating comprises determining the respective memory allocation for each respective layer based at least in part on a resource constraint of a target device. The subject technology compiles the NN code into a binary format. The subject technology generates a package for deploying the compiled NN code on the target device.

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