-
公开(公告)号：US11748666B2
公开(公告)日：2023-09-05
申请号：US15347875
申请日：2016-11-10
发明人： Minwei Feng , Yufei Ren , Yandong Wang , Li Zhang , Wei Zhang
摘要： A machine receives a first set of global parameters from a global parameter server. The first set of global parameters includes data that weights one or more operands used in an algorithm that models an entity type. Multiple learner processors in the machine execute the algorithm using the first set of global parameters and a mini-batch of data known to describe the entity type. The machine generates a consolidated set of gradients that describes a direction for the first set of global parameters in order to improve an accuracy of the algorithm in modeling the entity type when using the first set of global parameters and the mini-batch of data. The machine transmits the consolidated set of gradients to the global parameter server. The machine then receives a second set of global parameters from the global parameter server, where the second set of global parameters is a modification of the first set of global parameters based on the consolidated set of gradients.
-
公开(公告)号：US11669780B2
公开(公告)日：2023-06-06
申请号：US16675555
申请日：2019-11-06
发明人： Li Zhang , Wei Zhang , Xiaodong Cui
IPC分类号： G06N20/20
CPC分类号： G06N20/20
摘要： Building machine learning models by receiving, a plurality of training process scores associated with the model parameter lists, determining, a best model parameter list according to the training process scores, determining a descendant model parameter list according to the best model parameter list, wherein the descendant parameter list comprises a portion of the best model parameter list, distributing the descendant model parameter list, conducting a model training process according to the descendant model parameter list, determining a training process score according to the descendant model parameter list, and sending the training process score for the descendant model parameter list.
-
公开(公告)号：US11645526B2
公开(公告)日：2023-05-09
申请号：US16911645
申请日：2020-06-25
发明人： Mo Yu , Li Zhang , Tamir Klinger , Xiaoxiao Guo
摘要： A method and a system for learning and applying neuro-symbolic multi-hop rules are provided. The method includes inputting training texts into a neural network as well as pre-defined entities. The training texts and the entities relate to a specific domain. The method also includes generating an entity graph made up of nodes and edges. The nodes represent the pre-defined entities, and the edges represent passages in the training texts with co-occurrence of the entities connected together by the edges. The method further includes determining a relation based on the passages for each of the pre-defined entities connected together by the edges, calculating a probability relating to the relation, generating a potential reasoning path between a head entity and a target entity. The method also includes learning a neuro-symbolic rule by converting the edges along the potential reasoning path into symbolic rules and combining those rules into the neuro-symbolic rule.
-
公开(公告)号：US20220188813A1
公开(公告)日：2022-06-16
申请号：US17120150
申请日：2020-12-12
摘要： A suspicious pattern can be detected within a transaction network of nodes. Nodes of the network are walked by determining if any adjacent node to a current node is within the suspicious pattern. If an adjacent node is within the suspicious pattern, that node is walked to. Based on the walk, a node sequence can be generated.
-
公开(公告)号：US11138494B2
公开(公告)日：2021-10-05
申请号：US15584136
申请日：2017-05-02
发明人： Minwei Feng , Yufei Ren , Yandong Wang , Li Zhang , Wei Zhang
摘要： A storage controller of a machine receives training data associated with a neural network model. The neural network model includes a plurality of layers, and the machine further including at least one graphics processing unit. The storage controller trains at least one layer of the plurality of layers of the neural network model using the training data to generate processed training data. A size of the processed data is less than a size of the training data. Training of the at least one layer includes adjusting one or more weights of the at least one layer using the training data. The storage controller sends the processed training data to at least one graphics processing unit of the machine. The at least one graphics processing unit is configured to store the processed training data and train one or more remaining layers of the plurality of layers using the processed training data.
-
公开(公告)号：US11100116B2
公开(公告)日：2021-08-24
申请号：US16175102
申请日：2018-10-30
发明人： Shiwan Zhao , Zhi Qiao , Zhi Hu Wang , Li Zhang , Zhong Su
IPC分类号： G06F16/00 , G06F16/2457 , G06F7/14 , G06F16/56 , G06F16/9535
摘要： A computer-implemented method for implementing separated attention on like and dislike items for personalized ranking includes performing an element-wise product on a user embedding and a final like item embedding to generate a first vector. The method further includes performing an element-wise product on the user embedding and a final dislike item embedding to generate a second vector. The method further includes computing a probability that the user prefers the like item to the dislike item based on the first and second vectors, and generating one or more item recommendations including one or more electronic images for the user using the probability.
-
公开(公告)号：US10950070B2
公开(公告)日：2021-03-16
申请号：US16130120
申请日：2018-09-13
发明人： Changhua Sun , Shiwan Zhao , Li Zhang , HongLei Guo , Zhong Su
摘要： A method, a device and a computer program product for managing a shared vehicle are proposed. In the method, first information about a user is obtained. The first information indicates a speed of at least one shared vehicle used by the user. A target vehicle is determined from the at least one shared vehicle based on the first information. Second information about the target vehicle is determined. The second information indicates respective speeds of the target vehicle moving at a plurality of time intervals. An abnormal state of the target vehicle is detected based on the second information. The abnormal state indicates that a malfunction occurs in the target vehicle.
-
公开(公告)号：US20200286378A1
公开(公告)日：2020-09-10
申请号：US16296525
申请日：2019-03-08
发明人： Zhi Hu Wang , Shiwan Zhao , Li Zhang , Jun Zhu
IPC分类号： G08G1/0967 , G08G1/01
摘要： A computer-implemented method, a device and a computer program product for managing a vehicle are proposed. The computer-implemented method comprises: a determining, by a device operatively coupled to one or more processing units, a potential road section associated with a current road section on which a first vehicle is moving, the potential road section being a road section to which the first vehicle potentially moves from the current road section; obtaining, by the device, a road condition of the potential road section, the road condition being generated at least based on monitoring records of a second vehicle moving on the potential road section; and in response to the road condition indicating that the potential road section is unsuitable for moving on, transmitting, by the device, an alert about the potential road section to the first vehicle.
-
公开(公告)号：US10750013B2
公开(公告)日：2020-08-18
申请号：US16237868
申请日：2019-01-02
发明人： Keke Cai , Bai Chen Deng , Dongxu Duan , Zhong Su , Li Zhang , Xiaolu Zhang , Shiwan Zhao
摘要： A method, system, and computer program product, include receiving a request for registration from a service provider, upon the service receiver having authorized the request for registration, registering characteristic information of the service call in a user device of a service receiver, and upon a lapse of time, deregistering the characteristic information from the user device.
-
公开(公告)号：US10649642B2
公开(公告)日：2020-05-12
申请号：US15070391
申请日：2016-03-15
发明人： Zai Cen , Jie Jiang , Wen Juan Nie , Qi Ruan , Li Zhang , Chao Xing Zhou
IPC分类号： G06F3/0486 , G06F3/0482
摘要： A method, executed by a computer, for remapping interface elements on a graphical user interface includes activating an action capture mode responsive to input from a user, receiving a selection of an interface element, responsive to input from the user that uses the action capture mode, adding an alias user interface element corresponding to the interface element to a shortcut group, and wherein activation of the alias user interface element performs an action corresponding to the interface element. A computer program product and computer system corresponding to the above method are also disclosed herein.
-
-
-
-
-
-
-
-
-
搜索结果
237 条记录 (耗时 0.029 秒)
