-
1.发明授权公开(公告)号：US12001937B2
公开(公告)日：2024-06-04
申请号：US18268665
申请日：2021-10-29
发明人： Ping Huang , Ruizhen Wu , Jingjing Chen , Lin Wang
IPC分类号： G06N3/04
CPC分类号： G06N3/04
摘要： Disclosed are a data processing method and apparatus based on an optical neural network, a computer-readable storage medium, and an optical neural network. The method includes: acquiring initial optical information and final output optical information as well as intermediate input optical information and intermediate output optical information at input/output ports of the phase shifter of an input optical signal in a case that beam-splitting ratios of the beam splitters of the two interference optical path structure satisfy a beam-splitting compensation condition; calculating parameters of the internal phase shifters of the two interference optical path structures in a case that the initial optical information and the intermediate input optical information as well as the intermediate output optical information and the final output optical information satisfy a preset beam-splitting condition of the optical neural network; and performing data processing by using the optical neural network based on the parameters.
-
2.发明授权公开(公告)号：US12117905B2
公开(公告)日：2024-10-15
申请号：US18044885
申请日：2021-09-29
发明人： Ruizhen Wu , Mingming Wang , Lin Wang
CPC分类号： G06F11/1448 , G06F11/1435 , G06F17/16
摘要： The present disclosure discloses a method and a system for performing check recovery based on Gaussian elimination, a apparatus, and a storage medium. The method includes: a disk array by using normal data blocks and normal check blocks is constructed, a first reference matrix constructed by using coding matrix rows corresponding to the normal data blocks and the normal check blocks is converted into an inverse matrix through Gaussian elimination; it is determined that coding matrix rows corresponding to a predetermined quantity of blocks, and a second reference matrix is constructed by using the coding matrix rows, the abnormal data blocks, and the abnormal check blocks; and the inverse matrix and the second reference matrix are multiplied to obtain a first matrix, the first matrix and the disk array are multiplied to obtain an output matrix, and original data are obtained according to the output matrix.
-
公开(公告)号：US11829696B2
公开(公告)日：2023-11-28
申请号：US18022122
申请日：2021-09-30
发明人： Peng Feng , Xinwu Shen , Ruizhen Wu , Fang Wang
IPC分类号： G06F30/347
CPC分类号： G06F30/347
摘要： A connection analysis method for a multi-port nested model and a medium. The method includes: acquiring instance information and nested relationships of a multi-port nested model, and building an instance relationship tree; reading port information and connection information of instances, and adding the port information and the connection information to the instance relationship tree; acquiring the port information and the connection information of the instances of each node layer by layer according to the instance relationship tree to build a connection dictionary; and acquiring port-to-port connection information of the instances by retrieving the connection dictionary to perform connection analysis on the multi-port nested model.
-
公开(公告)号：US11989588B2
公开(公告)日：2024-05-21
申请号：US18025635
申请日：2021-09-29
发明人： Tangzhi Feng , Ruizhen Wu , Jian Cui , Hongbin Yu
CPC分类号： G06F9/5016 , G06F9/544 , G06F12/023 , G06F12/0292 , G06F2212/1016
摘要： A method for managing a shared memory, including: setting a master core, applying, by the master core, to a system for idle hugepage blocks, mapping the idle hugepage blocks to a virtual address space of the master core, and sorting the hugepage blocks in an ascending order of physical address size of the hugepage blocks; dividing, depending on whether the physical addresses are continuous, the hugepage blocks sorted into segments; in response to determining that there are segments satisfying the memory demand of the subsystem, sorting the segments satisfying the memory demand of the subsystem in a descending order of lengths thereof, and remapping the sorted segments to obtain segments having both continuous virtual addresses and continuous real addresses; and in response to determine that there is a segment satisfying the memory demand of the system, releasing hugepage blocks other than the segment satisfying the memory demand of the system.
-
公开(公告)号：US11893479B1
公开(公告)日：2024-02-06
申请号：US18267431
申请日：2021-11-30
发明人： Jingjing Chen , Ruizhen Wu , Ping Huang , Lin Wang
IPC分类号： G06N3/067
CPC分类号： G06N3/067
摘要： A method for realizing a Hadamard product, a device and a storage medium, includes: acquiring a plurality of to-be-treated optical signals with unequal wavelengths; inputting the to-be-treated optical signals into a wavelength division multiplexer; by using the wavelength division multiplexer, feeding the to-be-treated optical signals to a micro-ring-resonator component, wherein the micro-ring-resonator component includes a plurality of micro-ring-resonator groups each of which is formed by two micro-ring resonators with equal radii; and applying a corresponding electric current to the micro-ring-resonator component, to obtain a result of the Hadamard product according to an outputted light intensity.
-
-
-
-
搜索结果
5 条记录 (耗时 0.013 秒)
