专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

81. 发明公开

EP0752702A1 Artificial neural network read channel 失效
标题翻译： Lesekanal mitkünstlichem神经元Netzwerk
公开(公告)号：EP0752702A1
公开(公告)日：1997-01-08
申请号：EP96106025.8
申请日：1996-04-17
申请人： Hewlett-Packard Company
发明人： Richardson, Kenneth G.
IPC分类号： G11B20/10 , G11B5/09 , H04L25/03
CPC分类号： G11B20/10518 , G11B5/09 , G11B20/10009 , H04L7/0062 , H04L7/02 , H04L7/10 , H04L25/03165 , H04L2025/03464
摘要： A magnetic read channel (200) employs an artificial neural network for reconstruction of a recorded magnetic signal and its corresponding synchronization signal. A magnetic read head (210) receives magnetic signals from a magnetic recording media (201) such as a magnetic tape or disk and converts it to an electronic signal. A preamplifier (215) receives and amplifies the electronic signal from the magnetic read head (210) to produce an amplified electronic signal. A delay line (251) receives the amplified electronic signal from the preamplifier (215), storing delayed successive representations of the received signal. An artificial neural network (250) receives the delayed successive representations from the delay line (251) for reconstruction of the originally recorded data signal. Prior to use in an application, the artificial neural network (250) is trained via a training method with a known training set of corresponding simultaneously generated data and clock pairs. Training the network with data having such known clock (synchronization) signal enables extraction of the synchronization signal from its nonlinear properties hidden within its corresponding data.
摘要翻译：磁读取通道（200）采用人造神经网络来重建记录的磁信号及其对应的同步信号。磁读头（210）从诸如磁带或磁盘的磁记录介质（201）接收磁信号，并将其转换为电子信号。前置放大器（215）接收并放大来自磁读头（210）的电子信号，以产生放大的电子信号。延迟线（251）从前置放大器（215）接收放大的电子信号，存储接收信号的延迟的连续表示。人造神经网络（250）从延迟线（251）接收用于重建原始记录的数据信号的延迟的连续表示。在应用程序中使用之前，人造神经网络（250）通过具有对应的同时生成的数据和时钟对的已知训练集合的训练方法进行训练。用具有这种已知时钟（同步）信号的数据训练网络能够从其对应数据中隐藏的非线性属性中提取同步信号。

82. 发明授权

EP0454445B1 Waveform equalizer using a neural network 失效
标题翻译：波形与神经
公开(公告)号：EP0454445B1
公开(公告)日：1996-07-03
申请号：EP91303700.8
申请日：1991-04-24
申请人： FUJITSU LIMITED
发明人： Kimoto, Takashi , Kawabata, Kazuo , Asakawa, Kazuo , Ohishi, Yasuyuki , Fukuda, Eisuke , Takano, Takeshi
IPC分类号： H04L25/03
CPC分类号： H04L25/03165 , G06N3/04 , H04L2025/03464

83. 发明公开

EP0708544A1 Dispositif de reconnaissance d'informations portées par un signal reçu 失效
标题翻译： Einrichtung zur Erkennung der von einem empfangenen信号getragenen信息
公开(公告)号：EP0708544A1
公开(公告)日：1996-04-24
申请号：EP95402290.1
申请日：1995-10-13
申请人： ALCATEL MOBILE COMMUNICATION FRANCE
发明人： Chiodini, Alain
IPC分类号： H04L25/03
CPC分类号： H04L25/03165 , H04L2025/03464
摘要： Dispositif de reconnaissance d'informations dans un signal reçu, lesdites informations étant représentées, suivant une convention utilisée à l'émission, par des formes élémentaires possibles de signal à émettre, caractérisé en ce qu'il comporte :

des moyens (1) dits de corrélation pour effectuer une corrélation entre le signal reçu et diverses formes de signal possibles, suivant ladite convention,
un réseau de neurones (2) opérant à partir des coefficients de corrélation issus desdits moyens de corrélation, l'apprentissage de ce réseau ayant été réalisé en lui appliquant, en entrée, des coefficients de corrélation correspondant à un signal reçu porteur d'informations données, tout en lui imposant en sortie lesdites informations données, et ce réseau fournissant des informations dites reconnues.
摘要翻译：该装置包括提供接收信号与不同类型的可能信号之间的相关性的相关装置（1）。神经网络（2）对相关系数进行操作，并根据输入处的系数的应用进行训练。相关系数对应于接收数据信号的载波。网络提供通过例如相关性识别的数据。在两到五个符号的持续时间。

84. 发明公开

EP4364366A1 TRANSMITTER, RECEIVER AND METHOD FOR TRANSMIT AND RECEIVE FILTERING IN A COMMUNICATION SYSTEM 审中-公开
公开(公告)号：EP4364366A1
公开(公告)日：2024-05-08
申请号：EP21737608.6
申请日：2021-06-28
申请人： Nokia Technologies Oy
发明人： AIT AOUDIA, Faycal , HOYDIS, Jakob
IPC分类号： H04L25/03 , H04L25/06
CPC分类号： H04L25/03834 , H04L25/067 , H04L25/03165

85. 发明公开

EP3202056A1 ALL-OPTICAL SILICON-PHOTONIC CONSTELLATION CONVERSION OF AMPLITUDE-PHASE MODULATION FORMATS 有权
标题翻译：幅相调制格式的全光学硅光子转换
公开(公告)号：EP3202056A1
公开(公告)日：2017-08-09
申请号：EP15845902.4
申请日：2015-10-01
申请人： B.G. Negev Technologies & Applications Ltd., at Ben-Gurion University , Bar-Ilan University
发明人： SADOT, Dan , ZALEVSKY, Zeev , YEMINY, Tomer
IPC分类号： H04B10/00
CPC分类号： H04B10/615 , H04B10/291 , H04B10/5161 , H04B10/54 , H04B10/541 , H04B10/548 , H04B10/5561 , H04B10/612 , H04B2210/516 , H04L25/03165
摘要： A method for performing optical constellation conversion, according to which each received symbol from a constellation of input symbols is optically split into M components and each component is multiplied by a first predetermined different complex weighing factor, to achieve M firstly weighted components with different amplitudes. Then a nonlinear processor optically performs a nonlinear transform on each M firstly weighted components, so as to obtain M outputs which are linearly independent, Finally, a linear processor optically performs a linear transform to obtain a new converted constellation by optically multiplying, in the complex plane, each of the M outputs by a second predetermined different complex weighing factor, to achieve M secondly weighted components and then summing the M secondly weighted components.
摘要翻译：一种用于执行光学星座转换的方法，根据该方法，来自输入符号的星座的每个接收到的符号被光学地分成M个分量，并且每个分量乘以第一预定不同的复数加权因子，以实现具有不同幅度的M个第一加权分量。然后，非线性处理器对每M个第一加权分量光学地执行非线性变换，以获得线性无关的M个输出。最后，线性处理器光学地执行线性变换，以通过光学地乘以复数平面，M个输出中的每一个输出第二预定不同的复数加权因子，以获得M个第二加权分量，然后对M个第二加权分量求和。

86. 发明公开

EP3020173A1 SYSTEM AND METHOD FOR ITERATIVE COMPENSATION FOR LINEAR AND NONLINEAR INTERFERENCE IN SYSTEM EMPLOYING FTN SYMBOL TRANSMISSION RATES 审中-公开
标题翻译：系统和方法的线性和非线性问题迭代补偿系统中的带符号FTN传输速率
公开(公告)号：EP3020173A1
公开(公告)日：2016-05-18
申请号：EP14822126.0
申请日：2014-07-08
申请人： Hughes Network Systems, LLC
发明人： BEIDAS, Bassel , SESHADRI, Rohit, Lyer , EROZ, Mustafa , LEE, Lin-nan
IPC分类号： H04L25/40
CPC分类号： H04L25/03006 , H04L1/0048 , H04L1/005 , H04L1/0054 , H04L25/0314 , H04L25/03165 , H04L25/03834 , H04L25/497
摘要： An approach for increasing transmission throughput of a non-linear wireless channel, and efficient decoding of the transmitted signal via a simplified receiver, is provided. A signal reflects a source signal, and includes linear inter-symbol interference based on a faster-than-Nyquist signaling rate and a tight frequency roll-off, and non-linear interference based on high-power amplification for transmission over the wireless channel. The signal is received over a non-linear wireless channel, and is processed via a plurality of decoding iterations. A set of soft information of a current decoding iteration is generated based on a current estimate of the source signal and a final set of soft information from a previous decoding iteration. The current estimate of the source signal is based on an estimate of the linear ISI and the non-linear interference, which is based on the final set of soft information from the previous decoding iteration.
摘要翻译：用于经由简化接收机增加非线性无线信道，其反式mitted信号的有效解码的传输吞吐量的方法中，提供。的信号反映了源信号，并且包括基于基于高功率放大用于传输通过无线信道快于奈奎斯特信号速率和一个紧频率滚降，和非线性干扰的线性符号间干扰。的信号被接收的非线性无线信道，并经由解码迭代的多元性被处理。一组的当前解码迭代的软信息，生成基于所述源信号的当前估计与来自先前解码迭代的最终集合的软信息。源极信号的当前估计是基于线性ISI和非线性干扰，所有这是基于最终集合的从先前的解码迭代的软信息的估计。

87. 发明授权

EP0498574B1 Waveform equalizer apparatus formed of neural network, and method of designing same 失效
标题翻译：用于波形均衡神经网络及其设计方法
公开(公告)号：EP0498574B1
公开(公告)日：1997-07-23
申请号：EP92300838.7
申请日：1992-01-31
申请人： VICTOR COMPANY OF JAPAN, LIMITED
发明人： Takahashi, Susumu
IPC分类号： H04L25/03 , G06F15/80 , G11B20/10 , G11B20/22 , H03H21/00
CPC分类号： G11B20/10518 , G06N3/063 , G11B5/035 , G11B5/09 , G11B7/004 , G11B20/10009 , G11B20/22 , H04L25/03165 , H04L2025/03464 , Y10S706/909

88. 发明公开

EP0683489A3 Learning type signal recording and reproducing apparatus 失效
标题翻译：与学习信号记录和再现装置。
公开(公告)号：EP0683489A3
公开(公告)日：1996-04-03
申请号：EP95107524.1
申请日：1995-05-17
申请人： MATSUSHITA ELECTRIC INDUSTRIAL CO., LTD.
发明人： Maruno, Susumu , Kouda, Toshiyuki , Imagawa, Taro
IPC分类号： G11B20/10
CPC分类号： H04L25/03165 , G11B20/10 , G11B20/10009 , H04L2025/03464
摘要： The signal recording and reproducing apparatus of this invention includes: a signal detector (7) for detecting a teacher signal and an information signal recorded on a recording medium; a converting section (2) for converting the teacher signal and the information signal detected by the signal detector into a reproduction teacher signal and a reproduction information signal, respectively, based on a predetermined conversion rule; and a teacher signal generator (3) for generating a reference teacher signal, wherein the teacher signal is first detected before the detection of the information signal, and the converting means includes a learning type waveform converting section for automatically establishing the predetermined conversion rule based on the reproduction teacher signal and the reference teacher signal.

89. 发明公开

EP0498574A3 Waveform equalizer apparatus formed of neural network, and method of designing same 失效
标题翻译：形成神经网络的波形均衡器装置及其设计方法
公开(公告)号：EP0498574A3
公开(公告)日：1993-05-19
申请号：EP92300838.7
申请日：1992-01-31
申请人： VICTOR COMPANY OF JAPAN, LIMITED
发明人： Takahashi, Susumu
IPC分类号： H04L25/03 , G06F15/80 , G11B20/10 , G11B20/22 , H03H21/00
CPC分类号： G11B20/10518 , G06N3/063 , G11B5/035 , G11B5/09 , G11B7/004 , G11B20/10009 , G11B20/22 , H04L25/03165 , H04L2025/03464 , Y10S706/909
摘要： A waveform equalizer for reducing distortion of a digital signal produced from a digital data recording and playback system or transmission system is formed of a neural network having fixed weighting coefficients. Respective values for the coefficients are established by generating a corresponding simulated neuron network, by software implementation using a computer, and by executing a neuron network learning operation using input values obtained from a distorted digital signal and teaching values obtained from an original digital signal which resulted in the distorted digital signal.

90. 发明公开

EP0498574A2 Waveform equalizer apparatus formed of neural network, and method of designing same 失效
标题翻译：用于波形均衡神经网络和设计方法相同。
公开(公告)号：EP0498574A2
公开(公告)日：1992-08-12
申请号：EP92300838.7
申请日：1992-01-31
申请人： VICTOR COMPANY OF JAPAN, LIMITED
发明人： Takahashi, Susumu
IPC分类号： H04L25/03 , G06F15/80 , G11B20/10 , G11B20/22 , H03H21/00
CPC分类号： G11B20/10518 , G06N3/063 , G11B5/035 , G11B5/09 , G11B7/004 , G11B20/10009 , G11B20/22 , H04L25/03165 , H04L2025/03464 , Y10S706/909
摘要： A waveform equalizer for reducing distortion of a digital signal produced from a digital data recording and playback system or transmission system is formed of a neural network having fixed weighting coefficients. Respective values for the coefficients are established by generating a corresponding simulated neuron network, by software implementation using a computer, and by executing a neuron network learning operation using input values obtained from a distorted digital signal and teaching values obtained from an original digital signal which resulted in the distorted digital signal.
摘要翻译：用于减少来自数字数据记录和再生系统或传送系统产生的数字信号的失真的波形均衡器被形成为具有固定的加权系数的神经网络的。对于系数相应的值是通过使用计算机生成相应的模拟神经网络，通过软件实现建立，并通过执行一个神经元网络使用从导致原始数字信号所获得的畸变数字信号和教学值获得的输入值学习手术在失真的数字信号。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式