US 12,217,139 B2
Transforming a trained artificial intelligence model into a trustworthy artificial intelligence model
Florian Büttner, Munich (DE); and Christian Tomani, Munich (DE)
Assigned to Siemens Aktiengesellschaft, Munich (DE)
Filed by Siemens Aktiengesellschaft, Munich (DE)
Filed on Nov. 11, 2021, as Appl. No. 17/524,204.
Application 17/524,204 is a continuation in part of application No. 16/653,415, filed on Oct. 15, 2019, granted, now 11,455,531.
Claims priority of application No. 20208211 (EP), filed on Nov. 17, 2020.
Prior Publication US 2022/0067588 A1, Mar. 3, 2022
Int. Cl. G06N 20/00 (2019.01); G06F 21/62 (2013.01)
CPC G06N 20/00 (2019.01) [G06F 21/6218 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A computer-implemented method for transforming a trained artificial intelligence model into a trustworthy artificial intelligence model, comprising:
providing the trained artificial intelligence model via a user interface of a webservice platform, providing a validation data set, which is based on training data of the trained artificial intelligence model,
generating generic samples by a computing component of the webservice platform based on the validation data set, wherein for generating the generic samples the validation data set is modified by a domain-drift, and
transforming the trained artificial intelligence model by optimizing a calibration based on the generic samples, wherein by optimizing the calibration, an uncertainty-awareness is represented in a confidence-level for any of the generic samples.