US 11,995,553 B2
Parameterization of a machine learning system for a control system
Konrad Groh, Stuttgart (DE)
Assigned to ROBERT BOSCH GMBH, Stuttgart (DE)
Appl. No. 17/252,524
Filed by Robert Bosch GmbH, Stuttgart (DE)
PCT Filed Aug. 13, 2019, PCT No. PCT/EP2019/071735
§ 371(c)(1), (2) Date Dec. 15, 2020,
PCT Pub. No. WO2020/057868, PCT Pub. Date Mar. 26, 2020.
Claims priority of application No. 102018216078.3 (DE), filed on Sep. 20, 2018.
Prior Publication US 2021/0271972 A1, Sep. 2, 2021
Int. Cl. G06N 3/08 (2023.01); G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/241 (2023.01); G06F 18/2431 (2023.01); G06N 3/082 (2023.01)
CPC G06N 3/082 (2013.01) [G06F 18/211 (2023.01); G06F 18/214 (2023.01); G06F 18/241 (2023.01); G06F 18/2431 (2023.01); G06N 3/08 (2013.01)] 14 Claims
OG exemplary drawing
 
13. A machine learning system whose hyperparameters are selected in such a way that the machine learning system is trained to reproduce actual classifications of correctly labeled training data better than actual classifications of not correctly labeled training data, wherein the hyperparameters are selected in such a way that for the trained machine learning system, a statistical frequency distribution of margins that result when the machine learning system is supplied with the not correctly labeled training data has two maxima as a function of the margins.