-
1.发明公开公开(公告)号：US20240152806A1
公开(公告)日：2024-05-09
申请号：US18388078
申请日：2023-11-08
Inventor： Hao WU , Cheng YANG
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A solution for generating a negative sample pair of a contrastive learning model is provided. In one method, a first data segment is obtained from a first data sequence in a plurality of data sequences for training the contrastive learning model, and a second data segment is obtained from a second data sequence in the plurality of data sequences. A data frame is selected from a further data sequence than the second data sequence in the plurality of data sequences. A third data segment is generated based on the second data segment and the data frame. A negative sample pair for training the contrastive learning model is determined based on the first data segment and the third data segment. Therefore, richer semantic information can be introduced into negative sample pairs in terms of appearance, and further the accuracy of the contrastive learning model can be improved.
-
公开(公告)号：US20240152816A1
公开(公告)日：2024-05-09
申请号：US18504931
申请日：2023-11-08
Inventor： Hao WU , Cheng YANG
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A method, apparatus, device, and medium for managing a contrastive learning model are provided. In one method, in a first training phase, a first contrastive learning model is generated by training the contrastive learning model with a first training sample set, a negative sample pair of the first training sample set comprising only data segments from different data sequences. In a second training phase, a second contrastive learning model is generated by training the first contrastive learning model with a second training sample set, a negative sample pair in the second training sample set comprising data segments from the same data sequence. Knowledge in terms of the appearance of the samples can be fully obtained in the first training phase, and knowledge in terms of the appearance and dynamics of the samples can be fully obtained in the second training, with example implementations of the present disclosure.
-
3.发明公开公开(公告)号：US20240152815A1
公开(公告)日：2024-05-09
申请号：US18503658
申请日：2023-11-07
Inventor： Hao WU , Cheng YANG
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: A solution for generating a positive sample pair of a contrastive learning model is provided. In one method, a first data segment and a second data segment are respectively obtained from a first data sequence in plurality of data sequences for training the contrastive learning model, the first data sequence comprising a plurality of data frames. A data frame is selected from a second data sequence in the plurality of data sequences. A third data segment is generated based on the second data segment and the data frame. A positive sample pair for training the contrastive learning model is determined using the first data segment and the third data segment. In this way, positive samples that are more difficult to distinguish can be provided, thereby increasing the accuracy of the contrastive learning model and improving the training efficiency and accuracy of downstream models.
-
-
Search Results
3
records
(took 0.021 seconds)
