公开(公告)号：US12260327B2

公开(公告)日：2025-03-25

申请号：US17210141

申请日：2021-03-23

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Xiaomin Fang ,  Fan Wang ,  Yelan Mo ,  Jingzhou He

IPC: G06N3/08 ,  G06F18/20 ,  G06N20/00

Abstract: The present application discloses an optimizer learning method and apparatus, an electronic device and a readable storage medium, which relates to the field of deep learning technologies. An implementation solution adopted by the present application during optimizer learning is: acquiring training data, the training data including a plurality of data sets each including neural network attribute information, neural network optimizer information, and optimizer parameter information; and training a meta-learning model by taking the neural network attribute information and the neural network optimizer information in the data sets as input and taking the optimizer parameter information in the data sets as output, until the meta-learning model converges. The present application can implement self-adaptation of optimizers, so as to improve generalization capability of the optimizers.

公开(公告)号：US20220004867A1

公开(公告)日：2022-01-06

申请号：US17210141

申请日：2021-03-23

Applicant: Beijing Baidu Netcom Science and Technology Co., Ltd.

Inventor： Xiaomin Fang ,  Fan Wang ,  Yelan Mo ,  Jingzhou He

IPC: G06N3/08 ,  G06K9/62

Abstract: The present application discloses an optimizer learning method and apparatus, an electronic device and a readable storage medium, which relates to the field of deep learning technologies. An implementation solution adopted by the present application during optimizer learning is: acquiring training data, the training data including a plurality of data sets each including neural network attribute information, neural network optimizer information, and optimizer parameter information; and training a meta-learning model by taking the neural network attribute information and the neural network optimizer information in the data sets as input and taking the optimizer parameter information in the data sets as output, until the meta-learning model converges. The present application can implement self-adaptation of optimizers, so as to improve generalization capability of the optimizers.

公开(公告)号：US11412070B2

公开(公告)日：2022-08-09

申请号：US16891822

申请日：2020-06-03

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Xiaomin Fang ,  Yaxue Chen ,  Lihang Liu ,  Lingke Zeng ,  Fan Wang ,  Jingzhou He

IPC: H04L67/50 ,  G06N5/04 ,  H04L67/55 ,  G06Q10/10 ,  G06N20/00 ,  G06Q10/04 ,  G06Q30/02

Abstract: Embodiment of the disclosure provide a method and apparatus for generating information. The method includes: acquiring vectors of a plurality of users, the vector being used to characterize behavior habits of the users; inputting the vectors of the plurality of users and push information pushed by a push system to the plurality of users into a feedback information generating model established in advance, to generate the feedback information of the plurality of users for the push information, wherein the feedback information generating model is used to characterize a corresponding relationship between the vectors, the push information and the feedback information; and generating an evaluation report of the push system based on the feedback information.

公开(公告)号：US11836222B2

公开(公告)日：2023-12-05

申请号：US17083704

申请日：2020-10-29

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Lihang Liu ,  Xiaomin Fang ,  Fan Wang ,  Jingzhou He

IPC: G06Q30/00 ,  G06F18/21 ,  G06N20/00 ,  G06F16/9535 ,  G06Q30/0207 ,  G05B19/418 ,  G06Q30/0601

CPC classification number: G06F18/2178 ,  G06F16/9535 ,  G06F18/2193 ,  G06N20/00 ,  G06Q30/0221 ,  G06Q30/0225 ,  G06Q30/0631

Abstract: A method and apparatus for optimizing a recommendation system, a device and a computer storage medium are described, which relates to the technical field of deep learning and intelligent search in artificial intelligence. A specific implementation solution is: taking the recommendation system as an agent, a user as an environment, each recommended content of the recommendation system as an action of the agent, and a long-term behavioral revenue of the user as a reward of the environment; and optimizing to-be-optimized parameters in the recommendation system by reinforcement learning to maximize the reward of the environment. The present disclosure can effectively optimize long-term behavioral revenues of users.