Patent · US Active

Method and device for transfer learning between modified tasks

US12321827B2 · kind B2 · utility

0Cited by

0References

10Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Danny Stoll · Rheinfelden (Baden), DE
Diane Wagner · Freiburg (Elbe), DE
Frank Hutter · Würzburg, DE
Joerg Franke · Bruchsal, DE
Simon Selg · Freiburg (Elbe), DE

Key dates

Filing date	Aug 5, 2021
Grant date	Jun 3, 2025
Priority date	—
Expiry date	Apr 4, 2044

Classification

Technology area (CPC G)Physics
CPC primaryG06N7/01
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for the transfer learning of hyperparameters of a machine learning algorithm. The method includes providing a current search space and a previous search space. A reduced search space is then created and candidate configurations are drawn repeatedly at random from the reduced search space and from the current search space, and the machine learning algorithm, parameterized in each case with the candidate configurations, is applied. A Tree Parzen Estimator (TPE) is then created as a function of the candidate solutions and the results of the machine learning algorithm parameterized with the candidate configurations, and the drawing of further candidate configurations from the current search space using the TPE is repeated multiple times, the TPE being updated upon each drawing.

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