公开(公告)号：US20230259762A1

公开(公告)日：2023-08-17

申请号：US17972302

申请日：2022-10-24

Applicant: SAMSUNG ELECTRONICS CO., LTD.

Inventor： Zhimeng JIANG ,  Kaixiong ZHOU ,  Zirui LIU ,  Li LI ,  Rui CHEN ,  Soo-Hyun CHOI ,  Xia HU

IPC: G06N3/08

CPC classification number: G06N3/08

Abstract: An artificial intelligence (AI) classifier is trained using supervised training and an effect of noise in the training data is reduced. The training data includes observed noisy labels. A posterior transition matrix (PTM) is used to minimize, in a statistical sense, a cross entropy between a noisy label and a function of the classifier output. A loss function using the PTM is provided to use in training the classifier. The classifier provides final output predictions with good performance even with the existence of noisy labels. Also, information fusion is included in the classifier training using the PTM and an estimated noise transition matrix (NTM) to reduce estimation error at the classifier output.