Patent · US Active

Gradient-based auto-tuning for machine learning and deep learning models

US11176487B2 · kind B2 · utility

5Cited by
5References
44Claims
0Family size

Assignee

Inventors

Key dates

Filing dateJan 31, 2018
Grant dateNov 16, 2021
Priority date
Expiry dateSep 19, 2040

Classification

  • Technology area (CPC G)Physics
  • CPC primaryG06N20/10
  • WIPO fieldComputer technology
  • WIPO sectorElectrical engineering

Abstract

Herein, horizontally scalable techniques efficiently configure machine learning algorithms for optimal accuracy and without informed inputs. In an embodiment, for each particular hyperparameter, and for each epoch, a computer processes the particular hyperparameter. An epoch explores one hyperparameter based on hyperparameter tuples. A respective score is calculated from each tuple. The tuple contains a distinct combination of values, each of which is contained in a value range of a distinct hyperparameter. All values of a tuple that belong to the particular hyperparameter are distinct. All values of a tuple that belong to other hyperparameters are held constant. The value range of the particular hyperparameter is narrowed based on an intersection point of a first line based on the scores and a second line based on the scores. A machine learning algorithm is optimally configured from repeatedly narrowed value ranges of hyperparameters. The configured algorithm is invoked to obtain a result.

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