Patent · US Active

Adaptation of deep learning models to resource constrained edge devices

US11928583B2 · kind B2 · utility

2Cited by
1References
19Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJul 8, 2019
Grant dateMar 12, 2024
Priority date
Expiry dateMay 22, 2042

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/0985
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Techniques for generating a set of Deep Learning (DL) models are described. An example method includes training an initial set of DL models using the training data, wherein a topology of each of the DL models is determined based on the parameters vector. The method also includes generating a set of estimate performance functions for each of the DL models in the initial set based on the set of edge-related metrics, and generating a plurality of objective functions based on the set of estimated performance functions. The method also includes generating a final DL model set based on the objective functions, receiving a user selection of a selected DL model from the final DL model set, and deploying the selected DL model to an edge device.

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