-
1.发明公开
公开(公告)号：EP4305823A1
公开(公告)日：2024-01-17
申请号：EP21719111.3
申请日：2021-04-14
-
公开(公告)号：EP4385268A1
公开(公告)日：2024-06-19
申请号：EP22704307.2
申请日：2022-01-21
CPC分类号： H04W72/27 , H04W72/535 , H04W24/02 , G06N3/092 , G06N3/098
-
3.发明公开
公开(公告)号：EP4310732A2
公开(公告)日：2024-01-24
申请号：EP23206103.6
申请日：2019-10-18
发明人： BELFIORE, Jean-Claude , PASCHOS, Georgios , TSILIMANTOS, Dimitrios , DESTOUNIS, Apostolos , VASSILARAS, Spyridon , COSTANTINI, Marina , LIAKOPOULOS, Nikolaos , NGUYEN, Van, Minh , DEBBAH, Merouane
IPC分类号： G06N3/063
摘要： A data processing system having a neural network architecture for receiving a binary network input and, in dependence on the binary network input, propagating signals via a plurality of processing nodes, in accordance with respective binary weights, to form a network output, the data processing system being configured to train a node by implementing an error correcting function to identify a set of binary weights which minimize, for a given input to the node, any error between an output of the node when formed in accordance with current binary weights of the node and a preferred output from the node and to update the binary weights of the node to be the identified weights. This training is performed without storing and/or using any higher arithmetic precision weights or other components.
-
公开(公告)号：EP4309079A1
公开(公告)日：2024-01-24
申请号：EP21716362.5
申请日：2021-03-31
-
5.发明公开
公开(公告)号：EP4035273A1
公开(公告)日：2022-08-03
申请号：EP19790200.0
申请日：2019-10-18
-
6.发明公开
公开(公告)号：EP4310732A3
公开(公告)日：2024-04-03
申请号：EP23206103.6
申请日：2019-10-18
发明人： BELFIORE, Jean-Claude , PASCHOS, Georgios , TSILIMANTOS, Dimitrios , DESTOUNIS, Apostolos , VASSILARAS, Spyridon , COSTANTINI, Marina , LIAKOPOULOS, Nikolaos , NGUYEN, Van, Minh , DEBBAH, Merouane
摘要： A data processing system having a neural network architecture for receiving a binary network input and, in dependence on the binary network input, propagating signals via a plurality of processing nodes, in accordance with respective binary weights, to form a network output, the data processing system being configured to train a node by implementing an error correcting function to identify a set of binary weights which minimize, for a given input to the node, any error between an output of the node when formed in accordance with current binary weights of the node and a preferred output from the node and to update the binary weights of the node to be the identified weights. This training is performed without storing and/or using any higher arithmetic precision weights or other components.
-
-
8.发明公开CHANNEL STATE INFORMATION ACQUISITION IN A MULTI-USER MULTIPLE-INPUT MULTIPLE-OUTPUT TRANSMISSION SCHEME 审中-公开多用户多输入多输出传输方案中的信道状态信息获取
公开(公告)号：EP3320625A1
公开(公告)日：2018-05-16
申请号：EP15751026.4
申请日：2015-08-20
发明人： DESTOUNIS, Apostolos , MASO,Marco
CPC分类号： H04B7/0452
摘要： Provided is a multi-user multiple-input multiple-output (MU-MIMO), transmitter, adapted to acquire channel state information (CSI), from a plurality of receivers. The transmitter is configured to operate a radio antenna array to establish signal paths between antennas of the antenna array and a plurality of receivers. The transmitter comprises a mapper configured to dynamically group, for a given time interval, the plurality of receivers to MU-MIMO groups, wherein the grouping is based on information indicating correlations between signal paths from the antennas to the receivers and a transmission priority of each receiver. The transmitter further comprises a selector configured to select, for the given time interval, receivers from which CSI is to be received, and to identify one or more of the MU-MIMO groups based on the selected receivers.
-
-
-
-
-
-
-
搜索结果
8 条记录 (耗时 0.011 秒)
