Patent · US Active

Data-based updating of the training of classifier networks

US11947625B2 · kind B2 · utility

0Cited by

0References

15Claims

0Family size

Assignee

Robert Bosch GmbH · DE

Inventors

Chaithanya Kumar Mummadi · Heimsheim, DE
Jan Hendrik Metzen · Hessenhöfe, DE
Kilian Rambach · Stuttgart, DE
Robin Hutmacher · Renningen, DE

Key dates

Filing date	Sep 20, 2021
Grant date	Apr 2, 2024
Priority date	—
Expiry date	Oct 8, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06N3/047
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

A method for training a neural network. The method includes providing learning input images and associated learning output data; providing auxiliary input images; generating modifications of these auxiliary input images by introducing at least one predefined change into them; supplying the modifications to the neural network; ascertaining predictions for the predefined change, using output data onto which the neural network maps the modifications; assessing deviations of the predictions from the predefined change, using an auxiliary cost function; optimizing parameters of the neural network to improve the assessment by the auxiliary cost function during further processing of auxiliary input images; supplying the learning input images to the neural network; assessing deviations of the output data, thus obtained, from the learning output data, using a main cost function; optimizing parameters of the neural network to improve the assessment by the main cost function during further processing of learning input images.

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