专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

71. 发明申请

US20100299296A1 ELECTRONIC LEARNING SYNAPSE WITH SPIKE-TIMING DEPENDENT PLASTICITY USING UNIPOLAR MEMORY-SWITCHING ELEMENTS 有权
标题翻译：使用单核存储器切换元件的具有SPIKE时序依赖性塑性的电子学习算法
公开(公告)号：US20100299296A1
公开(公告)日：2010-11-25
申请号：US12470403
申请日：2009-05-21
申请人： Dharmendra S. Modha , Rohit S. Shenoy
发明人： Dharmendra S. Modha , Rohit S. Shenoy
IPC分类号： G06N3/08 , G06N3/04 , G06N3/063
CPC分类号： G06N3/049 , G06N3/0635
摘要： According to embodiments of the invention, a system, method and computer program product producing spike-dependent plasticity in an artificial synapse. In an embodiment, a method includes: receiving a pre-synaptic spike in an electronic component; receiving a post-synaptic spike in the electronic component; in response to the pre-synaptic spike, generating a pre-synaptic pulse that occurs a predetermined period of time after the received pre-synaptic spike; in response to the post-synaptic spike, generating a post-synaptic pulse that starts at a baseline value and reaches a first voltage value a first period of time after the post-synaptic spike, followed by a second voltage value a second period of time after the post synaptic spike, followed by a return to the baseline voltage a third period of time after the post-synaptic spike; applying the generated pre-synaptic pulse to a pre-synaptic node of a synaptic device that includes a uni-polar, two-terminal bi-stable device in series with a rectifying element; and applying the generated post-synaptic pulse to a post-synaptic node of the synaptic device, wherein the synaptic device changes from a first conductive state to a second conductive state based on the value of input voltage applied to its pre and post-synaptic nodes, wherein the resultant state of the conductance of the synaptic device after the pre- and post-synaptic pulses are applied thereto depends on the relative timing of the received pre-synaptic spike with respect to the post synaptic spike.
摘要翻译：根据本发明的实施例，在人造突触中产生尖峰依赖可塑性的系统，方法和计算机程序产品。在一个实施例中，一种方法包括：在电子部件中接收突触前突起; 接收电子元件中的突触后尖峰; 响应于突触前尖峰，产生在接收到的突触前尖峰之后发生预定时间段的突触前脉冲; 响应于突触后尖峰，产生在基线值开始并在突触后尖峰之后的第一时间段达到第一电压值的后突触后脉冲，随后是第二时间段的第二电压值后突触尖峰后，再次回到基线电压第三个时间段后突触后尖峰; 将产生的突触前脉冲应用于包括与整流元件串联的单极性双端双稳态器件的突触器件的突触前节点; 以及将所产生的突触后脉冲应用于所述突触装置的突触后结点，其中所述突触装置基于施加到其前和后突触节点的输入电压的值从第一导通状态改变到第二导通状态其中将突触前装置和突触后脉冲之后的突触装置的电导的结果状态施加到其上取决于所接收的突触前尖峰相对于突触后尖峰的相对时间。

72. 发明申请

US20100057653A1 DEVICE AND METHOD RESPONSIVE TO INFLUENCES OF MIND 有权
标题翻译：对MIND影响的设备和方法
公开(公告)号：US20100057653A1
公开(公告)日：2010-03-04
申请号：US12312570
申请日：2007-11-19
申请人： Scott A. Wilber
发明人： Scott A. Wilber
IPC分类号： G06N3/063 , G06F7/58 , G06N3/02
CPC分类号： G06F7/588 , G06F7/58 , G06N3/0635
摘要： V An anomalous effect detector (100, 130, 300, 800, 830, 840, 900, 930) responsive to an influence of mind comprises a source of non-deterministic random numbers, SNDRN, (104, 134, 310), a phase-sensitive filter (108, 140, 170, 320), and a results interface (110, 160, 340). In some embodiments, the phase-sensitive filter comprises a complex filter (170). An artificial sensory neuron (802, 810, 820, 906) comprises a SNDRN. Preferably, several artificial sensory neurons (802, 906) are grouped in a small volume. An analog artificial sensory detector (800) comprises a plurality of analog artificial sensory neurons (802), an abstracting processor (804) and a control or feedback unit (806). Some embodiments include an artificial neural network (850). An artificial consciousness network (900) contains a plurality of artificial neural networks (902, 914). One of the artificial neural networks (914) comprises an activation pattern meta-analyzer. An artificial consciousness device comprises a cluster (936) of artificial consciousness networks, a sensory input device (932) to provide sensory input signals (933) to the input of one or more ANNs in ACD (930), and an output device (938).
摘要翻译： V响应于心灵影响的异常效应检测器（100,130,300,800,830,408,900,930）包括非确定性随机数的源SNDRN（104,134,310），相位敏感过滤器（108,140,170,320）和结果界面（110,160,340）。在一些实施例中，相敏滤波器包括复数滤波器（170）。人造感觉神经元（802,810,820,906）包括SNDRN。优选地，将几个人造感觉神经元（802,906）分组成小体积。模拟人造感觉检测器（800）包括多个模拟人造感觉神经元（802），抽象处理器（804）和控制或反馈单元（806）。一些实施例包括人造神经网络（850）。人工意识网络（900）包含多个人造神经网络（902,914）。人造神经网络之一（914）包括激活模式元分析器。人造意识装置包括人造意识网络的群集（936），向ACD（930）中的一个或多个ANN的输入提供感觉输入信号（933）的感觉输入设备（932）和输出设备（938））。

73. 发明授权

US07401058B2 Artificial neuron with phase-encoded logic 有权
标题翻译：具有相位编码逻辑的人造神经元
公开(公告)号：US07401058B2
公开(公告)日：2008-07-15
申请号：US11118087
申请日：2005-04-29
申请人： Howard E. Michel , David P. Rancour
发明人： Howard E. Michel , David P. Rancour
IPC分类号： G06F15/18 , G06N3/08
CPC分类号： G06N3/049 , G06N3/0635
摘要： An artificial neuron includes an aggregator that combines a plurality of input signals. The value state of each of the input signals is encoded in a phase thereof. The artificial neuron also includes an actuator in communication with the aggregator. The actuator is configured to provide an output signal having a value state encoded in a phase thereof. The value state of the output signal may be selected on the basis of the value states of the input signals. The value state of each of the input signals and/or the output signal may be a logical state.
摘要翻译：人造神经元包括组合多个输入信号的聚合器。每个输入信号的值状态被编码在其相位中。人造神经元还包括与聚集器通信的致动器。致动器被配置为提供具有在其相位中编码的值状态的输出信号。可以基于输入信号的值状态来选择输出信号的值状态。每个输入信号和/或输出信号的值状态可以是逻辑状态。

74. 发明申请

US20080162391A1 SOLVING THE DISTAL REWARD PROBLEM THROUGH LINKAGE OF STDP AND DOPAMINE SIGNALING 有权
标题翻译：通过STDP和DOPAMINE信号的链接解决远程问题
公开(公告)号：US20080162391A1
公开(公告)日：2008-07-03
申请号：US11963403
申请日：2007-12-21
申请人： Eugene M. Izhikevich
发明人： Eugene M. Izhikevich
IPC分类号： G06N3/08
CPC分类号： G06N3/049 , G06N3/02 , G06N3/063 , G06N3/0635 , G06N99/005
摘要： In Pavlovian and instrumental conditioning, rewards typically come seconds after reward-triggering actions, creating an explanatory conundrum known as the distal reward problem or the credit assignment problem. How does the brain know what firing patterns of what neurons are responsible for the reward if (1) the firing patterns are no longer there when the reward arrives and (2) most neurons and synapses are active during the waiting period to the reward? A model network and computer simulation of cortical spiking neurons with spike-timing-dependent plasticity (STDP) modulated by dopamine (DA) is disclosed to answer this question. STDP is triggered by nearly-coincident firing patterns of a presynaptic neuron and a postsynaptic neuron on a millisecond time scale, with slow kinetics of subsequent synaptic plasticity being sensitive to changes in the extracellular dopamine DA concentration during the critical period of a few seconds after the nearly-coincident firing patterns. Random neuronal firings during the waiting period leading to the reward do not affect STDP, and hence make the neural network insensitive to this ongoing random firing activity. The importance of precise firing patterns in brain dynamics and the use of a global diffusive reinforcement signal in the form of extracellular dopamine DA can selectively influence the right synapses at the right time.
摘要翻译：在巴甫洛夫和工具条件下，奖励通常会在奖励触发动作之后几秒钟，创造一个被称为远程奖励问题或信用分配问题的解释性难题。如果（1）当奖励到达时，射击模式不再在那里，（2）大多数神经元和突触在等待期间是活跃的，大脑如何知道什么是神经元对于奖励的触发模式？披露了由多巴胺（DA）调制的具有刺激时间依赖性可塑性（STDP）的皮层加标神经元的模型网络和计算机模拟来回答这个问题。 STDP在几毫秒的时间尺度上由突触前神经元和突触后神经元的几乎一致的发射模式触发，随后突触可塑性的缓慢动力学对于在数秒后的几秒的关键时期内对细胞外多巴胺DA浓度的变化敏感几乎一致的射击模式。导致奖励的等待期间的随机神经元激发不会影响STDP，因此使神经网络对这种持续的随机射击活动不敏感。精确射击模式在脑动力学中的重要性以及以细胞外多巴胺DA的形式使用全局扩散加强信号的选择可以选择性地在正确的时间影响右侧突触。

75. 发明申请

US20080154822A1 Systems and methods for creating an artificial neural network 审中-公开
标题翻译：用于创建人造神经网络的系统和方法
公开(公告)号：US20080154822A1
公开(公告)日：2008-06-26
申请号：US11589539
申请日：2006-10-30
申请人： Daniel Curt Loeser , David Edward Maestas
发明人： Daniel Curt Loeser , David Edward Maestas
IPC分类号： G06E1/00
CPC分类号： G06N3/0635
摘要： A neural network system is described. The neural network system includes an artificial neural network including a plurality of neurons. One of the neurons includes an analog electrical circuit and the neurons are interconnected.
摘要翻译：描述神经网络系统。神经网络系统包括包括多个神经元的人造神经网络。其中一个神经元包括模拟电路，神经元相互连接。

76. 发明授权

US06844582B2 Semiconductor device and learning method thereof 失效
标题翻译：半导体器件及其学习方法
公开(公告)号：US06844582B2
公开(公告)日：2005-01-18
申请号：US10434358
申请日：2003-05-09
申请人： Michihito Ueda , Kenji Toyoda , Takashi Ohtsuka , Kiyoyuki Morita
发明人： Michihito Ueda , Kenji Toyoda , Takashi Ohtsuka , Kiyoyuki Morita
IPC分类号： G06N3/063 , G11C27/00 , H01L21/8246 , H01L21/8247 , H01L21/84 , H01L27/115 , H01L27/12 , H01L45/00 , H01L29/76 , H01L27/108 , G06F15/18 , G06G7/00
CPC分类号： H01L27/11502 , G06N3/0635 , G11C11/54 , G11C27/00 , H01L21/84 , H01L27/115 , H01L27/11507 , H01L27/11521 , H01L27/11585 , H01L27/1159 , H01L27/1203 , H01L45/06 , H01L45/1206 , H01L45/144
摘要： A learning method of a semiconductor device of the present invention comprises a neuro device having a multiplier as a synapse in which a weight varies according to an input weight voltage, and functioning as a neural network system that processes analog data, comprising a step A of inputting predetermined input data to the neuro device and calculating an error between a target value of an output of the neuro device with respect to the input data and an actual output, a step B of calculating variation amount in the error by varying a weight of the multiplier thereafter, and a step C of varying the weight of the multiplier based on the variation amount in the error, wherein in the steps B and C, after inputting a reset voltage for setting the weight to a substantially constant value to the multiplier as the weight voltage, the weight is varied by inputting the weight voltage corresponding to the weight to be varied.
摘要翻译：本发明的半导体器件的学习方法包括具有倍增器作为突触的神经器件，其中重量根据输入重量电压而变化，并且用作处理模拟数据的神经网络系统，其包括步骤A的步骤A 向神经装置输入预定的输入数据并计算神经装置的输出的目标值相对于输入数据与实际输出之间的误差;步骤B，通过改变神经元的重量来计算误差的变化量; 之后的乘法器，以及基于误差变化量来改变乘法器的权重的步骤C，其中在步骤B和C中，在输入用于将权重设定为基本恒定值的复位电压之后，重量电压，通过输入与要变化的重量相对应的重量电压来改变重量。

77. 发明授权

US06744299B2 Electronic array having nodes and methods 失效
标题翻译：具有节点和方法的电子阵列
公开(公告)号：US06744299B2
公开(公告)日：2004-06-01
申请号：US10271874
申请日：2002-10-15
申请人： H. Mario Geysen
发明人： H. Mario Geysen
IPC分类号： H03K1762
CPC分类号： G06N3/0635 , G05F3/222 , G05F3/265
摘要： An electronic network comprises a plurality of nodes that each comprise a current input and a current output, and at least one transistor arranged as a first current mirror and a second current mirror. The first and the second current mirrors are complementary to each other such that an output of the first current mirror is operably connected to an input of the second current mirror. Resistive connections connect the nodes such that the output of one or more of the nodes is operably connected to the input of one or more of the nodes.
摘要翻译：电子网络包括多个节点，每个节点包括电流输入和电流输出，以及布置为第一电流镜和第二电流镜的至少一个晶体管。第一和第二电流镜彼此互补，使得第一电流镜的输出可操作地连接到第二电流镜的输入。电阻连接连接节点，使得一个或多个节点的输出可操作地连接到一个或多个节点的输入。

78. 发明授权

US6011295A Neural network active pixel cell 失效
标题翻译：神经网络有源像素单元
公开(公告)号：US6011295A
公开(公告)日：2000-01-04
申请号：US898062
申请日：1997-07-22
申请人： Richard Billings Merrill , Albert Bergemont , Min-hwa Chi
发明人： Richard Billings Merrill , Albert Bergemont , Min-hwa Chi
IPC分类号： G06N3/063 , G06G7/16
CPC分类号： G06N3/0635
摘要： An active pixel image cell which includes a photosensor, active devices for control of the sensor and readout of a signal representing the intensity of light to which the sensor is exposed, and a neuron MOSFET transistor which "both amplifies the signal from the photosensor and" simulates the behavior of a human neuron. An integrated neural network and imaging array may be formed by interconnecting a group of such pixels. Digital signal processing algorithms used for image processing may be implemented at the pixel level by appropriate interconnections between the output signals from the photosensor of surrounding pixels and the neuron MOSFET.
摘要翻译：包括光传感器的有源像素图像单元，用于控制传感器的有源器件和表示传感器所暴露的光的强度的信号的读出，以及“两者都放大来自光电传感器的信号”的神经元晶体管，模拟人类神经元的行为。可以通过将一组这样的像素互连来形成集成神经网络和成像阵列。用于图像处理的数字信号处理算法可以通过来自周围像素的光电传感器的输出信号和神经元MOSFET之间的适当互连在像素级上实现。

79. 发明授权

US5937399A Semiconductor integrated circuit 失效
标题翻译：半导体集成电路
公开(公告)号：US5937399A
公开(公告)日：1999-08-10
申请号：US663248
申请日：1996-06-11
申请人： Tadahiro Ohmi , Tadashi Shibata , Koji Kotani
发明人： Tadahiro Ohmi , Tadashi Shibata , Koji Kotani
IPC分类号： G06F15/18 , G06N3/063 , H01L21/8247 , H01L27/10 , H01L27/115 , H01L29/788 , H01L29/792
CPC分类号： G06N3/0635
摘要： A semiconductor integrated circuit includes one or more neuron MOS transistors on a substrate. The MOS transistor comprises a semiconductor region of one conductivity type, source and drain regions of opposite conductivity type disposed in this region, floating gate disposed on an insulating film between the source and drain regions, and a plurality of input coupling electrodes making capacitive coupling with the floating gate through the insulating film, wherein the floating gate is connected to at least one switching device.
摘要翻译： PCT No.PCT / JP94 / 02001 Sec。 371日期：1996年6月11日 102（e）日期1996年6月11日PCT 1994年11月29日PCT公布。第WO95 / 15581号公报日期：1995年6月8日半导体集成电路在衬底上包括一个或多个神经元MOS晶体管。 MOS晶体管包括一个导电类型的半导体区域，设置在该区域中的具有相反导电类型的源极和漏极区域，浮置栅极设置在源极和漏极区域之间的绝缘膜上，以及多个输入耦合电极，所述浮栅通过所述绝缘膜，其中所述浮动栅极连接到至少一个开关装置。

80. 发明授权

US5914868A Multiplier and neural network synapse using current mirror having low-power mosfets 失效
标题翻译：使用具有低功率MOSFET的电流镜的乘法器和神经网络突触
公开(公告)号：US5914868A
公开(公告)日：1999-06-22
申请号：US940004
申请日：1997-09-29
申请人： Il Song Han , Young Jae Choi , Dae Hwan Kim
发明人： Il Song Han , Young Jae Choi , Dae Hwan Kim
IPC分类号： G06G7/14 , G06F7/44 , G06G7/163 , G06G7/60 , G06N3/063 , H02M3/18 , G05F3/16 , G06F1/04
CPC分类号： G06G7/163 , G06N3/0635
摘要： A multiplier and a neural network synapse capable of removing nonlinear current using current mirror circuits. The multiplier produces a linear current by using MOS transistors operating in a nonsaturation region. The multiplier includes a first current mirror including a plurality of MOS transistors to form a first current and a second current mirror including a plurality of MOS transistors to form a second current, wherein the second current mirror is coupled in parallel to the first current mirror. As a result, the multiplier outputs an output current by subtracting a second current from said first current.
摘要翻译：乘法器和神经网络突触能够使用电流镜像电路去除非线性电流。乘法器通过使用在非饱和区域中工作的MOS晶体管产生线性电流。乘法器包括：包括多个MOS晶体管以形成第一电流的第一电流镜和包括多个MOS晶体管以形成第二电流的第二电流镜，其中第二电流镜并联耦合到第一电流镜。结果，乘法器通过从所述第一电流减去第二电流来输出输出电流。

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