-
公开(公告)号:US20230053009A1
公开(公告)日:2023-02-16
申请号:US17972459
申请日:2022-10-24
Applicant: Snap Inc.
Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
-
公开(公告)号:US11544553B1
公开(公告)日:2023-01-03
申请号:US16448749
申请日:2019-06-21
Applicant: Snap Inc.
Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
-
公开(公告)号:US11893489B2
公开(公告)日:2024-02-06
申请号:US17972459
申请日:2022-10-24
Applicant: Snap Inc.
CPC classification number: G06N3/08 , G06F18/24 , G06F18/295 , G06N3/045
Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
-
公开(公告)号:US20240127064A1
公开(公告)日:2024-04-18
申请号:US18543330
申请日:2023-12-18
Applicant: Snap Inc.
CPC classification number: G06N3/08 , G06F18/24 , G06F18/295 , G06N3/045
Abstract: A computer-implement method comprises: training a classifier with labeled data from a dataset; classifying, by the trained classifier, unlabeled data from the dataset; providing, by the classifier to a policy gradient, a reward signal for each data/query pair; transferring, by the classifier to a ranker, learning; training, by the policy gradient, the ranker; ranking data from the dataset based on a query; and retrieving data from the ranked data in response to the query.
-
-
-