US 11,715,043 B2
Semantics preservation for machine learning models deployed as dependent on other machine learning models
Edouard Godfrey, Sunnyvale, CA (US); Gianpaolo Fasoli, Redwood City, CA (US); and Kuangyu Wang, Cupertino, CA (US)
Assigned to Apple Inc., Cupertino, CA (US)
Filed by Apple Inc., Cupertino, CA (US)
Filed on Feb. 28, 2020, as Appl. No. 16/805,625.
Claims priority of provisional application 62/812,888, filed on Mar. 1, 2019.
Prior Publication US 2020/0279192 A1, Sep. 3, 2020
Int. Cl. G06N 20/20 (2019.01); G06N 20/00 (2019.01); G06V 10/00 (2022.01); G06V 10/70 (2022.01)
CPC G06N 20/20 (2019.01) [G06N 20/00 (2019.01)] 20 Claims
OG exemplary drawing
 
1. A method comprising:
receiving assessment values determined by a first machine learning model deployed on a client electronic device, the assessment values being indicative of classifications of input data and the assessment values being associated with constraint data that comprises a probability distribution of the assessment values with respect to the classifications of the input data;
applying the assessment values determined by the first machine learning model to a second machine learning model to determine the classifications of the input data;
determining whether accuracies of the classifications determined by the second machine learning model conform with the probability distribution for corresponding assessment values determined by the first machine learning model; and
retraining the first machine learning model when the accuracies of the classifications determined by the second machine learning model do not conform with the probability distribution of the corresponding assessment values determined by the first machine learning model.