Patent · US Active

Systems, methods, and computer-readable media for parallel stochastic gradient descent with linear and non-linear activation functions

US11295231B2 · kind B2 · utility

0Cited by
4References
15Claims
0Family size

Assignee

Inventors

Key dates

Filing dateMay 22, 2017
Grant dateApr 5, 2022
Priority date
Expiry dateDec 13, 2039

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N3/08
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Systems, methods, and computer-readable media are disclosed for parallel stochastic gradient descent using linear and non-linear activation functions. One method includes: receiving a set of input examples; receiving a global model; and learning a new global model based on the global model and the set of input examples by iteratively performing the following steps: computing a plurality of local models having a plurality of model parameters based on the global model and at least a portion of the set of input examples; computing, for each local model, a corresponding model combiner based on the global model and at least a portion of the set of input examples; and combining the plurality of local models into the new global model based on the current global model and the plurality of corresponding model combiners.

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