Patent · US Active

Training of machine learning systems for image processing

US12254675B2 · kind B2 · utility

0Cited by

2References

14Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Samuel Mueller · Freiburg im Breisgau, DE
Andre Biedenkapp · Freiburg im Breisgau, DE
Frank Hutter · Würzburg, DE

Key dates

Filing date	Jan 12, 2022
Grant date	Mar 18, 2025
Priority date	—
Expiry date	May 6, 2043

Classification

Technology area (CPC G)Physics
CPC primaryG06V10/776
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A computer-implemented method for training a machine learning system including: initializing parameters of the machine learning system and a metaparameter. Repeatedly carrying out the following as a loop: providing a batch of training data points and manipulating the provided training data points or a training method for optimizing the parameters of the machine learning system or a structure of the machine learning system based on the metaparameter. Ascertaining a cost function as a function of instantaneous parameters of the machine learning system and of the instantaneous metaparameters. Adapting the instantaneous parameters as a function of an ascertained first gradient, which has been ascertained with respect to the instantaneous parameters via the ascertained cost function for the training data points, and adapting the metaparameter as a function of a second gradient, which has been ascertained with respect to the metaparameter used in the preceding step via the ascertained cost function.

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