公开(公告)号：US20230229897A1

公开(公告)日：2023-07-20

申请号：US18173591

申请日：2023-02-23

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Stepan Alekseevich Komkov ,  Aleksandr Aleksandrovich Petiushko ,  Ivan Leonidovich Mazurenko ,  Jiang Li

IPC: G06N3/0499 ,  G06V10/82 ,  G06V40/16

CPC classification number: G06N3/0499 ,  G06V10/82 ,  G06V40/172

Abstract: The present disclosure relates to processing input data by a neural network. Methods and apparatuses of some embodiments process the input data by at least one layer of the neural network and obtain thereby a feature tensor. Then, the distribution of the obtained feature tensors estimated. Another distribution is obtained. Such other distribution may be a distribution of another input data, or a distribution obtained by combining a plurality of distributions obtained for respective plurality of some input data. Then a distance value indicative of a distance between the two distributions is calculated and based thereon, a characteristic of the input data is determined. The characteristic may be pertinence to a certain class of data or a detection of out-of-distribution data or determination of reliability of a class determination or the like.