Patent · US Active

Systems and methods for accelerating hessian-free optimization for deep neural networks by implicit preconditioning and sampling

US9601109B2 · kind B2 · utility

6Cited by
0References
20Claims
0Family size

Assignee

Inventors

Key dates

Filing dateSep 29, 2014
Grant dateMar 21, 2017
Priority date
Expiry dateApr 24, 2035

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG10L15/16
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

A method for training a deep neural network, comprises receiving and formatting speech data for the training, preconditioning a system of equations to be used for analyzing the speech data in connection with the training by using a non-fixed point quasi-Newton preconditioning scheme, and employing flexible Krylov subspace solvers in response to variations in the preconditioning scheme for different iterations of the training.

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