-
公开(公告)号：US11537896B2
公开(公告)日：2022-12-27
申请号：US16424945
申请日：2019-05-29
申请人： Intel Corporation
摘要： Systems, methods, computer program products, and apparatuses to determine, by a neural network based on training data related to wireless signals exchanged by a device and a plurality of wireless access points in an environment, a respective distance between the device and each wireless access point, receive location data related to a respective location of each wireless access point of the plurality of wireless access points, determine a geometric cost of the neural network based on a geometric cost function, the respective distances, and the received location data, and train a plurality of values of the neural network based on a backpropagation and the determined geometric cost.
-
公开(公告)号：US20210204243A1
公开(公告)日：2021-07-01
申请号：US16729104
申请日：2019-12-27
申请人： Intel Corporation
发明人： Jeongsik Choi , Yang-Seok Choi
摘要： Methods, apparatuses, and computer readable media for parameter update for range-based positioning. An apparatus of a station (STA) for parameter update for range-based positioning, the apparatus including processing circuitry configured to perform a distance estimating method with access points (APs) to determine distance estimates between the APs and the STA, the distant estimating method including parameters, and configured to determine a location of the STA based on the distance estimates between the APs and the STAs and locations of the APs. The processing circuitry further configured to: update the parameters by subtracting from a parameter of the parameters a learning rate times a derivative of a cost function with respect to the parameter, where the cost function is based on the determined location of the STA, the locations of the APs, and the distance estimates between the APs and the STA.
-
公开(公告)号：US11778584B2
公开(公告)日：2023-10-03
申请号：US16729104
申请日：2019-12-27
申请人： Intel Corporation
发明人： Jeongsik Choi , Yang-Seok Choi
CPC分类号： H04W64/006 , G01S5/0215 , H04B1/16 , H04W84/12
摘要： Methods, apparatuses, and computer readable media for parameter update for range-based positioning. An apparatus of a station (STA) for parameter update for range-based positioning, the apparatus including processing circuitry configured to perform a distance estimating method with access points (APs) to determine distance estimates between the APs and the STA, the distant estimating method including parameters, and configured to determine a location of the STA based on the distance estimates between the APs and the STAs and locations of the APs. The processing circuitry further configured to: update the parameters by subtracting from a parameter of the parameters a learning rate times a derivative of a cost function with respect to the parameter, where the cost function is based on the determined location of the STA, the locations of the APs, and the distance estimates between the APs and the STA.
-
公开(公告)号：US20230101962A1
公开(公告)日：2023-03-30
申请号：US17987409
申请日：2022-11-15
申请人： Intel Corporation
摘要： Systems, methods, computer program products, and apparatuses to determine, by a neural network based on training data related to wireless signals exchanged by a device and a plurality of wireless access points in an environment, a respective distance between the device and each wireless access point, receive location data related to a respective location of each wireless access point of the plurality of wireless access points, determine a geometric cost of the neural network based on a geometric cost function, the respective distances, and the received location data, and train a plurality of values of the neural network based on a backpropagation and the determined geometric cost.
-
公开(公告)号：US11887007B2
公开(公告)日：2024-01-30
申请号：US17987409
申请日：2022-11-15
申请人： Intel Corporation
CPC分类号： G06N3/084 , G01S5/0278 , G01S5/14 , G06N3/04 , H04B7/0626 , H04W24/08
摘要： Systems, methods, computer program products, and apparatuses to determine, by a neural network based on training data related to wireless signals exchanged by a device and a plurality of wireless access points in an environment, a respective distance between the device and each wireless access point, receive location data related to a respective location of each wireless access point of the plurality of wireless access points, determine a geometric cost of the neural network based on a geometric cost function, the respective distances, and the received location data, and train a plurality of values of the neural network based on a backpropagation and the determined geometric cost.
-
公开(公告)号：US20230068386A1
公开(公告)日：2023-03-02
申请号：US17790950
申请日：2020-12-26
申请人： Intel Corporation
发明人： Mustafa Riza Akdeniz , Arjun Anand , Nageen Himayat , Amir S. Avestimehr , Ravikumar Balakrishnan , Prashant Bhardwaj , Jeongsik Choi , Yang-Seok Choi , Sagar Dhakal , Brandon Gary Edwards , Saurav Prakash , Amit Solomon , Shilpa Talwar , Yair Eliyahu Yona
IPC分类号： G06N20/00
摘要： The apparatus of an edge computing node, a system, a method and a machine-readable medium. The apparatus includes a processor to perform rounds of federated machine learning training including: processing client reports from a plurality of clients of the edge computing network; selecting a candidate set of clients from the plurality of clients for an epoch of the federated machine learning training; causing a global model to be sent to the candidate set of clients; and performing the federated machine learning training on the candidate set of clients. The processor may perform rounds of federated machine learning training including: obtaining coded training data from each of the selected clients; and performing machine learning training on the coded training data.
-
-
-
-
-
搜索结果
6 条记录 (耗时 0.013 秒)
