利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

96 条记录 (耗时 0.018 秒)

    ARTIFICIAL NEURON
    84.
    发明申请
    ARTIFICIAL NEURON 审中-公开
    人造神经元

    公开(公告)号：US20160196489A1

    公开(公告)日：2016-07-07

    申请号：US14916127

    申请日：2014-08-27

    申请人： PHILIPS LIGHTING HOLDING B.V.

    发明人： FREDERIC ALEXANDRE GUILLANNEUF ,  MARCELLINUS PETRUS CAROLUS MICHAEL KRIJN

    IPC分类号： G06N3/067

    CPC分类号： G06N3/067 ,  G06N3/0675 ,  G11C7/005 ,  G11C7/1081

    摘要： The present invention relates to an optical device (101, 201, 305). The present invention may be implemented as optical artificial neurons. The optical device comprises an optically transmissive light-receiving device (102) which may be a photodiode, an optically transmissive light-emitting device (104, 304) such as a light-emitting diode, an optically transmissive processor (103) comprising a memory storage device (106). The light-emitting device and the light-receiving device are electrically connected to the processor which is configured to control the light-emitting device to emit an optical signal (307, 313) based on a first optical signal received by the light-receiving device. The optical device comprises an address which is transmitted with the optical signal. The address of may be recognized by the processor when processing a received optical signal and is used by the processor to determine to control the light-emitting device to emit an optical signal or not.

    摘要翻译： 本发明涉及光学装置（101,201,305）。 本发明可以实现为光学人造神经元。 光学装置包括光透射光接收装置（102），其可以是光电二极管，诸如发光二极管的光学透射发光装置（104,304），光学透射处理器（103），包括存储器 存储装置（106）。 发光装置和光接收装置电连接到处理器，处理器被配置为基于由光接收装置接收的第一光信号来控制发光装置发射光信号（307,313） 。 光学装置包括与光信号一起传输的地址。 当处理接收到的光信号时，处理器可以识别地址，并且由处理器使用该地址来确定控制发光器件发射光信号。

    HYBRID INTERCONNECT STRATEGY FOR LARGE-SCALE NEURAL NETWORK SYSTEMS
    85.
    发明申请
    HYBRID INTERCONNECT STRATEGY FOR LARGE-SCALE NEURAL NETWORK SYSTEMS 审中-公开
    用于大规模神经网络系统的混合互连策略

    公开(公告)号：US20140067742A1

    公开(公告)日：2014-03-06

    申请号：US14012183

    申请日：2013-08-28

    申请人： International Business Machines Corporation

    发明人： Yasunao Katayama ,  Daiju Nakano ,  Toshiyuki Yamane

    IPC分类号： G06N3/04

    CPC分类号： G06N3/067 ,  G06N3/04

    摘要： A plurality of chips arranged in a certain layout so as to face free space, and one or more optical elements are included. In the case where signal traffic for electrical communication with a given chip exceeds or is expected to exceed a certain threshold, a plurality of chips involved in communication routing of the excess signal traffic are identified, part of related signal traffic that crosses the plurality of identified chips is converted from an electric signal into an optical signal to re-route the excess signal traffic, and paths of the related signal traffic are dynamically adapted from fixed wired paths between the plurality of chips to optical communication paths formed in the free space.

    摘要翻译： 以一定的布局布置成面向自由空间的多个芯片，以及一个或多个光学元件。 在与给定芯片进行电通信的信号业务超过或预期超过一定阈值的情况下，识别涉及多余信号业务的通信路由的多个芯片，其中相关信号业务的一部分穿过多个识别的 芯片从电信号转换为光信号以重新路由多余的信号业务，并且相关信号业务的路径动态地从多个芯片之间的固定有线路径适配到在自由空间中形成的光通信路径。

    Optical neural network
    86.
    发明授权
    Optical neural network 有权
    光学神经网络

    公开(公告)号：US07847225B2

    公开(公告)日：2010-12-07

    申请号：US12602072

    申请日：2008-05-02

    申请人： Shin Yokoyama

    发明人： Shin Yokoyama

    IPC分类号： G06F15/18 ,  G06E3/00

    CPC分类号： G06N3/067 ,  H01L27/15 ,  H01S5/0425 ,  H01S5/183 ,  H01S5/423 ,  H01S2301/18

    摘要： An input layer outputs light having a relatively narrow emission angle distribution to a middle layer as an output signal if the signal level of input signal is relatively high and outputs light having a relatively broad emission angle distribution to the middle layer as the output signal if the signal level of input signal is relatively low. The middle layer outputs light having a relatively narrow emission angle distribution as an output signal to an output layer if the signal level of the output signal from input layer is relatively high and outputs light having a relatively broad emission angle distribution to the output layer as an output signal if the signal level of the output signal from the input layer is relatively low.

    摘要翻译： 如果输入信号的信号电平相对较高，则输入层将具有较窄发射角分布的光输出到中间层作为输出信号，并将具有相对宽的发射角分布的光作为输出信号输出作为输出信号，如果 输入信号的信号电平相对较低。 如果来自输入层的输出信号的信号电平相对较高，则中间层将具有相对窄的发射角分布的光作为输出信号输出到输出层，并将具有相对宽的发射角分布的光输出到输出层，作为 如果来自输入层的输出信号的信号电平相对较低，则输出信号。

    OPTICAL NEURAL NETWORK
    87.
    发明申请
    OPTICAL NEURAL NETWORK 有权
    光学神经网络

    公开(公告)号：US20100176278A1

    公开(公告)日：2010-07-15

    申请号：US12602072

    申请日：2008-05-02

    申请人： Shin Yokoyama

    发明人： Shin Yokoyama

    IPC分类号： H01L31/147

    CPC分类号： G06N3/067 ,  H01L27/15 ,  H01S5/0425 ,  H01S5/183 ,  H01S5/423 ,  H01S2301/18

    摘要： An input layer outputs light having a relatively narrow emission angle distribution to a middle layer as an output signal if the signal level of input signal is relatively high and outputs light having a relatively broad emission angle distribution to the middle layer as the output signal if the signal level of input signal is relatively low. The middle layer outputs light having a relatively narrow emission angle distribution as an output signal to an output layer if the signal level of the output signal from input layer is relatively high and outputs light having a relatively broad emission angle distribution to the output layer as an output signal if the signal level of the output signal from the input layer is relatively low.

    摘要翻译： 如果输入信号的信号电平相对较高，则输入层将具有较窄发射角分布的光输出到中间层作为输出信号，并将具有相对宽的发射角分布的光作为输出信号输出作为输出信号，如果 输入信号的信号电平相对较低。 如果来自输入层的输出信号的信号电平相对较高，则中间层将具有相对窄的发射角分布的光作为输出信号输出到输出层，并将具有相对宽的发射角分布的光输出到输出层，作为 如果来自输入层的输出信号的信号电平相对较低，则输出信号。

    Multi-layer opto-electronic neural network
    88.
    发明授权
    Multi-layer opto-electronic neural network 失效
    多层光电神经网络

    公开(公告)号：US5497253A

    公开(公告)日：1996-03-05

    申请号：US99882

    申请日：1993-07-30

    申请人： Harold M. Stoll ,  James J. Reis

    发明人： Harold M. Stoll ,  James J. Reis

    IPC分类号： G02F3/00 ,  G03H1/04 ,  G03H1/16 ,  G03H1/18 ,  G06E3/00 ,  G06G7/60 ,  G06K9/74 ,  G06K9/76 ,  G06N3/067 ,  G02B27/46

    CPC分类号： G06K9/745 ,  G03H1/0248 ,  G03H1/16 ,  G06E3/001 ,  G06N3/067 ,  G03H1/0005 ,  G03H1/265 ,  G03H2001/0066 ,  G03H2260/54

    摘要： A pattern recognition apparatus and a method for operating same. The apparatus includes a volume holographic medium (4) having a plurality of Fourier-space volume holograms representing pattern templates stored within. The apparatus further includes a spatial light modulator (1) and a phase encoder (2). The phase encoder has an output optically coupled to the medium by a first Fourier transform lens (3). The spatial light modulator spatially modulates a spatially uniform laser beam (7) in accordance with an unknown pattern. The two-dimensional phase encoder causes the spatially modulated laser beam to be spatially distributed prior to application to the medium. The apparatus also includes a detector (6, 11) having an input optically coupled by a second Fourier transform lens (5) means to an angular spectrum of plane waves generated by the medium in response to the output of the spatial modulator, phase encoder, and first Fourier lens. The detector detects plane waves that correspond to vector inner products generated within medium (4) in response to the unknown pattern. The apparatus further contains a means (12) for nonlinearly processing the output of detector (6, 11) and a means (13) by which the output of nonlinear processing means (12) may be temporarily stored.

    摘要翻译： 模式识别装置及其操作方法。 该装置包括具有代表存储在其中的图案模板的多个傅立叶空间体积全息图的体积全息介质（4）。 该装置还包括空间光调制器（1）和相位编码器（2）。 相位编码器具有通过第一傅立叶变换透镜（3）光耦合到介质的输出。 空间光调制器根据未知图案空间调制空间均匀的激光束（7）。 二维相位编码器使空间调制的激光束在施加到介质之前被空间分布。 该装置还包括检测器（6,11），该检测器具有由第二傅里叶变换透镜（5）光学耦合的输入装置，该输入装置响应于空间调制器，相位编码器的输出，由介质产生的平面波的角谱， 和第一傅里叶透镜。 检测器检测对应于在介质（4）内响应未知图案产生的向量内积的平面波。 该装置还包括用于非线性处理检测器（6,11）的输出的装置（12）和用于临时存储非线性处理装置（12）的输出的装置（13）。

    Volume-holographic inner product processor
    89.
    发明授权
    Volume-holographic inner product processor 失效
    体全息内积处理器

    公开(公告)号：US5235439A

    公开(公告)日：1993-08-10

    申请号：US811589

    申请日：1991-12-20

    申请人： Harold M. Stoll

    发明人： Harold M. Stoll

    IPC分类号： G06E3/00 ,  G06K9/74 ,  G06N3/067

    CPC分类号： G06K9/745 ,  G06E3/001 ,  G06N3/067 ,  G03H1/265 ,  G03H2001/0066 ,  G03H2260/54

    摘要： A pattern recognition apparatus and a method for operating same. The apparatus includes a volume holographic medium (4) having a plurality of Fourier-space volume holograms representing pattern templates stored within. The apparatus further includes a spatial light modulator (1) and a phase encoder (2). The phase encoder has an output optically coupled to the medium by a first Fourier transform lens (3). The spatial light modulator spatially modulates a spatially uniform laser beam (7) in accordance with an unknown pattern. The two-dimensional phase encoder causes the spatially modulated laser beam to be spatially distributed prior to application to the medium. The apparatus further includes a detector (6, 11) having an input optically coupled by a second Fourier transform lens (5) means to an angular spectrum of plane waves generated by the medium in response to the output of the spatial modulator, phase encoder, and first Fourier lens. The detector detects plane waves that correspond to vector inner products generated within medium (4) in response to the unknown pattern.

    摘要翻译： 模式识别装置及其操作方法。 该装置包括具有代表存储在其中的图案模板的多个傅立叶空间体积全息图的体积全息介质（4）。 该装置还包括空间光调制器（1）和相位编码器（2）。 相位编码器具有通过第一傅立叶变换透镜（3）光耦合到介质的输出。 空间光调制器根据未知图案空间调制空间均匀的激光束（7）。 二维相位编码器使空间调制的激光束在施加到介质之前被空间分布。 该装置还包括检测器（6,11），其具有由第二傅里叶变换透镜（5）光学耦合的输入装置，该输入装置响应于空间调制器，相位编码器的输出而由介质产生的平面波的角谱， 和第一傅里叶透镜。 检测器检测对应于在介质（4）内响应未知图案产生的向量内积的平面波。

    Continuous-time optical neural network process
    90.
    发明授权
    Continuous-time optical neural network process 失效
    连续光学神经网络过程

    公开(公告)号：US5132835A

    公开(公告)日：1992-07-21

    申请号：US562175

    申请日：1990-08-03

    申请人： Harold M. Stoll ,  Li-Shing Lee

    发明人： Harold M. Stoll ,  Li-Shing Lee

    IPC分类号： G06E3/00 ,  G06K9/74 ,  G06N3/067

    CPC分类号： G06K9/74 ,  G06E3/001 ,  G06N3/067 ,  G03H1/265 ,  G03H2001/0066 ,  G03H2260/54

    摘要： An all-optical, continuous-time, recurrent neural network is disclosed which is capable of executing a broad class of energy-minimizing neural net algorithms. The network is a resonator which contains a saturable, two-beam amplifier; two volume holograms; and a linear, two-beam amplifier. The saturable amplifier permits, through the use of a spatially patterned signal beam, the realization of a two-dimensional optical neuron array; the two volume holograms provide adaptive, global network interconnectivity; and the linear amplifier supplies sufficient resonator gain to permit convergent operation of the network.

    摘要翻译： 公开了一种全光学，连续时间，循环神经网络，其能够执行广泛的能量最小化神经网络算法。 该网络是包含可饱和的双光束放大器的谐振器; 两个体积全息图; 和一个线性双光束放大器。 可饱和放大器允许通过使用空间图案化信号光束实现二维光学神经元阵列; 两个体积全息图提供自适应全球网络互连; 并且线性放大器提供足够的谐振器增益以允许网络的收敛操作。