Methods and apparatus for coding for interference network

    公开(公告)号:US11018795B2

    公开(公告)日:2021-05-25

    申请号:US15514092

    申请日:2015-09-29

    摘要: The disclosed techniques allow for transmitting a signal stream from a sender to a receiver in an environment including multiple senders and receivers. The technique for the sender decomposes a data stream from the sender into multiple substreams, encodes a substream by a codeword, further superimposes multiple codewords to form a signal stream in an asynchronous manner, and transmits the signal stream to the receiver. A codeword can span over multiple blocks. The receiver receives a first codeword stream from a first sender, receives a second codeword stream from a second sender, the two codeword streams may be received at the same time as one signal, and decodes the first codeword stream and second codeword stream over a sliding window of multiple blocks.

    Method and apparatus for learning stochastic inference models between multiple random variables with unpaired data

    公开(公告)号:US11615317B2

    公开(公告)日:2023-03-28

    申请号:US16886429

    申请日:2020-05-28

    IPC分类号: G06N20/20 G06N3/088 G06N3/04

    摘要: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

    METHOD AND APPARATUS FOR LEARNING STOCHASTIC INFERENCE MODELS BETWEEN MULTIPLE RANDOM VARIABLES WITH UNPAIRED DATA

    公开(公告)号:US20210319326A1

    公开(公告)日:2021-10-14

    申请号:US16886429

    申请日:2020-05-28

    IPC分类号: G06N3/08 G06N3/04

    摘要: A system and method for operating a neural network. In some embodiments, the neural network includes a variational autoencoder, and the training of the neural network includes training the variational autoencoder with a plurality of samples of a first random variable; and a plurality of samples of a second random variable, the plurality of samples of the first random variable and the plurality of samples of the second random variable being unpaired, the training of the neural network including updating weights in the neural network based on a first loss function, the first loss function being based on a measure of deviation from consistency between: a conditional generation path from the first random variable to the second random variable, and a conditional generation path from the second random variable to the first random variable.

    Method and apparatus for forwarding signal for wireless multi-hop communication

    公开(公告)号:US09826459B2

    公开(公告)日:2017-11-21

    申请号:US14599318

    申请日:2015-01-16

    摘要: A wireless multi-hop network includes a source node, at least one relay node, and a destination node. Each relay node is configured to perform partial decoding on a received signal including at least one previous-hop transmission signal according to a predefined function to calculate a function signal for the at least one previous-hop transmission signal, and encode the function signal and transmit the encoded function signal to a next hop. A destination node includes a receiver configured to obtain a received signal comprising a combination of a plurality of transmission signals for transmission by a source node and to be relayed by at least one relay node, and a decoder configured to configure a decoder graph corresponding to channel coding by the source node and relay nodes and to joint-decode the received signal according to the decoder graph to detect information blocks from the received signal.

    METHOD AND APPARATUS FOR FORWARDING SIGNAL FOR WIRELESS MULTI-HOP COMMUNICATION
    9.
    发明申请
    METHOD AND APPARATUS FOR FORWARDING SIGNAL FOR WIRELESS MULTI-HOP COMMUNICATION 有权
    用于无线多通信通信的信号转发方法和装置

    公开(公告)号:US20150201366A1

    公开(公告)日:2015-07-16

    申请号:US14599318

    申请日:2015-01-16

    IPC分类号: H04W40/22

    摘要: A wireless multi-hop network includes a source node, at least one relay node, and a destination node. Each relay node is configured to perform partial decoding on a received signal including at least one previous-hop transmission signal according to a predefined function to calculate a function signal for the at least one previous-hop transmission signal, and encode the function signal and transmit the encoded function signal to a next hop. A destination node includes a receiver configured to obtain a received signal comprising a combination of a plurality of transmission signals for transmission by a source node and to be relayed by at least one relay node, and a decoder configured to configure a decoder graph corresponding to channel coding by the source node and relay nodes and to joint-decode the received signal according to the decoder graph to detect information blocks from the received signal.

    摘要翻译: 无线多跳网络包括源节点,至少一个中继节点和目的节点。 每个中继节点被配置为根据预定义的功能对包括至少一个上一跳传输信号的接收信号执行部分解码,以计算所述至少一个上一跳传输信号的功能信号,并对功能信号进行编码并传输 编码的功能信号到下一跳。 目的地节点包括:接收机,被配置为获得包括多个传输信号的组合的接收信号,用于由源节点传输并由至少一个中继节点中继;以及解码器,被配置为配置对应于信道的解码器图 由源节点和中继节点进行编码,并根据解码器图对接收到的信号进行联合解码,以从接收到的信号检测信息块。

    Apparatus and method for receiving signal in wireless communication system

    公开(公告)号:US10454535B2

    公开(公告)日:2019-10-22

    申请号:US15891146

    申请日:2018-02-07

    IPC分类号: H04B7/0413 H04B7/08 H04L25/03

    摘要: The present disclosure relates to a pre-5th-Generation (5G) or 5G communication system to be provided for supporting higher data rates Beyond 4th-Generation (4G) communication system such as Long Term Evolution (LTE). According to various embodiments, in a multiple-input multiple-output wireless communication system, a receiving apparatus may include at least one processor and at least one transceiver. The at least one transceiver may be configured to receive a signal including a plurality of symbols, perform Successive Interference Cancellation (SIC) related to a first symbol of the plurality of symbols on the received signal to obtain a processed signal, determine symbol-sums by applying an equalization matrix for integer forcing to the processed signal, and determine information words corresponding to the plurality of symbols based on the symbol-sums.