专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明申请

WO2016154440A1 SPARSE INFERENCE MODULES FOR DEEP LEARNING 审中-公开
标题翻译：用于深度学习的稀疏参数模块
公开(公告)号：WO2016154440A1
公开(公告)日：2016-09-29
申请号：PCT/US2016/024017
申请日：2016-03-24
申请人： HRL LABORATORIES, LLC , PILLY, Praveen, K. , STEPP, Nigel, D. , SRINIVASA, Narayan
发明人： PILLY, Praveen, K. , STEPP, Nigel, D. , SRINIVASA, Narayan
IPC分类号： G06N5/04 , G06N3/08 , G06F15/18 , G06F17/00
CPC分类号： G06N3/08 , G06F15/18 , G06K9/4628 , G06K9/6249 , G06K9/6272 , G06K9/64 , G06N3/0454 , G06N3/0481 , G06N5/04
摘要： Described is a sparse inference module that can be incorporated into a deep learning •system. For example, the deep learning system includes a plurality of hierarchical feature channel layers, each feature channel layer having a set of filters. A plurality of sparse inference modules can be included, such that a sparse inference module resides electronically within each feature channel layer. Each sparse inference module is configured to receive data and match the data against a plurality of pattern templates to generate a. degree of match value for each of the pattern templates, wife the degree of match values being sparsified such that only those degree of match values that exceed a predetermined threshold, or a fixed number of the top degree of match values, are provided to subsequent feature, channels in the plurality of hierarchical feature channels, while other, losing degree of match values are quenched to zero.
摘要翻译：描述了一个稀疏的推理模块，可以并入深入学习系统。例如，深度学习系统包括多个分层特征信道层，每个特征信道层具有一组过滤器。可以包括多个稀疏推理模块，使得稀疏推理模块电子地驻留在每个特征通道层内。每个稀疏推理模块被配置为接收数据并使数据与多个模式模板匹配以产生a。每个模式模板的匹配值的程度，妻子将匹配值的程度进行稀疏化，使得只有超过预定阈值的匹配值的程度或最大匹配值的固定数量被提供给随后的特征，多个分层特征通道中的通道，而另一些失去匹配值的程度被淬灭到零。

2. 发明申请

WO2015073713A1 SYSTEM FOR CONTROLLING BRAIN MACHINE INTERFACES AND NEURAL PROSTHETIC SYSTEMS 审中-公开
标题翻译：控制脑机接口和神经系统的系统
公开(公告)号：WO2015073713A1
公开(公告)日：2015-05-21
申请号：PCT/US2014/065537
申请日：2014-11-13
申请人： HRL LABORATORIES, LLC , DE SAPIO, Vincent , SRINIVASA, Narayan
发明人： DE SAPIO, Vincent , SRINIVASA, Narayan
IPC分类号： A61F2/68 , A61F2/72
CPC分类号： A61F2/68 , A61F2/72 , A61F2002/701 , A61F2002/7615 , G06N3/049
摘要： Described is a system for controlling a torque controlled prosthetic device given motor intent inferred from neuroimaging data. The system includes at least one torque controlled prosthetic device operably connected with one or more processors. Further, the system is configured to receive neuroimaging data of a user from a neuroimaging device and decode the neuroimaging data to infer spatial motion intent of the user, where the spatial motion intent includes desired motion commands of the torque controlled prosthetic device represented in a coordinate system. The system thereafter executes, with a prosthesis controller, the motion commands as torque commands to cause the torque controlled prosthetic device to move according to the spatial motion intent of the user.
摘要翻译：描述了一种用于控制由神经成像数据推断的给定电机意图的扭矩控制假体装置的系统。该系统包括与一个或多个处理器可操作地连接的至少一个扭矩控制的假体装置。此外，该系统被配置为从神经成像设备接收用户的神经成像数据并且解码神经成像数据以推断用户的空间运动意图，其中空间运动意图包括在坐标中表示的扭矩控制的假体装置的期望运动命令系统。该系统随后用假体控制器执行运动命令作为扭矩命令，以使扭矩控制的假体装置根据使用者的空间运动意图而移动。

3. 发明申请

WO2012166821A2 SPIKE DOMAIN CIRCUIT AND MODELING METHOD 审中-公开
标题翻译： SPIKE域电路和建模方法
公开(公告)号：WO2012166821A2
公开(公告)日：2012-12-06
申请号：PCT/US2012/040043
申请日：2012-05-30
申请人： HRL LABORATORIES, LLC , CRUZ-ALBRECHT, Jose , PETRE, Peter , SRINIVASA, Narayan
发明人： CRUZ-ALBRECHT, Jose , PETRE, Peter , SRINIVASA, Narayan
IPC分类号： H03M3/00
CPC分类号： G06N3/049 , G06N3/063 , H03M3/43 , H03M3/454
摘要： A spike domain circuit responsive to analog and/or spike domain input signals. Has a hysteresis quantizer for generating a spike domain output signal z(t); a one bit DAC having an input coupled to receive the spike domain output signal z(t) and an output coupled to a current summing node; and a second order filter stage having two inputs, one coupled to receive the spike domain output signal z(t); the other coupled to receive current summed at said current summing node. The second order filter stage has an output coupled to an input of the hysteresis quantizer. The current summing node also receives signals related to the analog and/or spike domain input signals for response. The circuit may serve as a neural node. Many such circuits may be used together to model neurons with complex biological dynamics.
摘要翻译：响应于模拟和/或尖峰域输入信号的尖峰域电路。具有用于产生尖峰域输出信号z（t）的滞后量化器; 具有耦合以接收尖峰域输出信号z（t）的输入和耦合到电流求和节点的输出的一比特DAC; 和具有两个输入的二阶滤波器级，一个被耦合以接收尖峰域输出信号z（t）; 另一个耦合以接收在所述当前求和节点处相加的电流。二阶滤波器级具有耦合到迟滞量化器的输入的输出。当前求和节点还接收与模拟和/或尖峰域输入信号有关的信号以作出响应。该电路可以用作神经节点。许多这样的电路可以一起使用以用复杂的生物动力学来模拟神经元。

4. 发明申请

WO2002086814A1 AN ON-LINE METHOD FOR SELF-ORGANIZED LEARNING AND EXTRACTION OF FUZZY RULES 审中-公开
标题翻译：自组织学习和提取模糊规则的在线方法
公开(公告)号：WO2002086814A1
公开(公告)日：2002-10-31
申请号：PCT/US2002/013069
申请日：2002-04-23
申请人： HRL LABORATORIES, LLC , SRINIVASA, Narayan , MEDASANI, Swarup, S.
发明人： SRINIVASA, Narayan , MEDASANI, Swarup, S.
IPC分类号： G06N7/02
CPC分类号： G06N7/023 , G06K9/00362
摘要： The present invention provides an improved method and system for training an on-line fuzzy interference network to generate a rule base, and a rule base generated thereby. Turning and applying a learning rule to the fuzzy rules generated by the fuzzy interference network in such a manner as to divorce the performance of the network from the number of input dimension allows the present invention to adapt a fuzzy inference network such as a SONFIN to be effective for the classification of high-dimensional data in problems requiring the use of a high number of dimensions such as occupant recognition in vehicles, weather forecasting, and economic forecasting.
摘要翻译：本发明提供了一种用于训练在线模糊干扰网络以生成规则库的改进方法和系统，以及由此产生的规则库。将模糊干扰网络所产生的模糊规则转换和应用于使得网络的性能与输入维数的离散的方式允许本发明使诸如SONFIN之类的模糊推理网络适应于有效地在需要使用诸如车辆中的乘客识别，天气预报和经济预测等大量维度的问题中对高维数据进行分类。

5. 发明申请

WO2014149070A1 NEURAL NETWORK AND METHOD OF PROGRAMMING 审中-公开
标题翻译：神经网络和编程方法
公开(公告)号：WO2014149070A1
公开(公告)日：2014-09-25
申请号：PCT/US2013/057724
申请日：2013-08-30
申请人： HRL LABORATORIES, LLC
发明人： SRINIVASA, Narayan , CHO, Youngkwan
IPC分类号： G06N3/02
CPC分类号： G06N3/08 , G06N3/049
摘要： A neural network, wherein a portion of the neural network comprises: a first array having a first number of neurons, wherein the dendrite of each neuron of the first array is provided for receiving an input signal indicating that a measured parameter gets closer to a predetermined value assigned to said neuron; and a second array having a second number of neurons, wherein the second number is smaller than the first number, the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of a plurality of neurons of the first array; the dendrite of each neuron of the second array forming an excitatory STDP synapse with the axon of neighboring neurons of the second array.
摘要翻译：神经网络，其中所述神经网络的一部分包括：具有第一数量的神经元的第一阵列，其中所述第一阵列的每个神经元的枝晶被提供用于接收输入信号，所述输入信号指示所测量的参数越接近预定的分配给所述神经元的值; 以及具有第二数量的神经元的第二阵列，其中所述第二数目小于所述第一数目，所述第二阵列的每个神经元的枝晶与所述第一阵列的多个神经元的轴突形成兴奋性STDP突触; 第二阵列的每个神经元的树突形成与第二阵列的相邻神经元的轴突的兴奋性STDP突触。

6. 发明申请

WO2014018078A1 NEURON CIRCUIT AND METHOD 审中-公开
标题翻译：神经电路和方法
公开(公告)号：WO2014018078A1
公开(公告)日：2014-01-30
申请号：PCT/US2012/065640
申请日：2012-11-16
申请人： HRL LABORATORIES, LLC
发明人： CRUZ-ALBRECHT, Jose , SRINIVASA, Narayan , YUNG, Micahel W.
IPC分类号： G06G7/60 , G06N3/02
CPC分类号： G06N3/02 , G06N3/049 , G06N3/0635
摘要： A spike domain asynchronous neuron circuit includes a first spike to exponential circuit for emulating kinetic dynamics at a neuron input and converting voltage spikes into exponentials, a first adjustable gain circuit for emulating homeostatic plasticity coupled to the first voltage-type spike exponential output and having a first current output, a neuron core circuit coupled to the first current output for emulating a neuron core and having a spike encoded voltage output, a filter and comparator circuit coupled to the spike encoded voltage output and having a gain control output coupled to the first adjustable gain circuit for controlling a gain of the first adjustable gain circuit, and an adjustable delay circuit for emulating an axonal delay coupled to the spike encoded voltage output and having an axonal delay output.
摘要翻译：尖峰域异步神经元电路包括用于模拟神经元输入处的动力学并将电压尖峰转换为指数的指数电路的第一尖峰，用于模拟耦合到第一电压型尖峰指数输出的稳态可塑性的第一可调增益电路，第一电流输出，耦合到第一电流输出的神经元核心电路，用于仿真神经元核并具有尖峰编码电压输出;耦合到尖峰编码电压输出的滤波器和比较器电路，并具有耦合到第一可调整电压的增益控制输出用于控制第一可调增益电路的增益的增益电路，以及用于模拟耦合到尖峰编码电压输出并具有轴突延迟输出的轴突延迟的可调延迟电路。

7. 发明申请

WO2017209886A2 AN EFFICIENT HYBRID METHOD FOR EGO-MOTION FROM VIDEOS CAPTURED USING AN AERIAL CAMERA 审中-公开
标题翻译：一种有效的混合方法用于从使用空中相机拍摄的视频中移动EGO
公开(公告)号：WO2017209886A2
公开(公告)日：2017-12-07
申请号：PCT/US2017/030673
申请日：2017-05-02
申请人： HRL LABORATORIES, LLC
发明人： CAO, Yongqiang , SRINIVASA, Narayan , RAO, Shankar, R.
CPC分类号： H04N5/144 , H04N19/527
摘要： Described is a system for compensating for ego-motion during video processing. The system generates an initial estimate of camera ego-motion of a moving camera for consecutive image frame pairs of a video of a scene using a projected correlation method, the camera configured to capture the video from a moving platform. An optimal estimation of camera ego-motion is generated using the initial estimate as an input to a valley search method or an alternate line search method. All independent moving objects are detected in the scene using the described hybrid method at superior performance compared to existing methods while saving computational cost.
摘要翻译：描述了一种用于在视频处理期间补偿自我运动的系统。该系统使用投影相关方法为场景的视频的连续图像帧对生成运动摄像机的摄像机自我运动的初始估计，该摄像机被配置为捕捉来自移动平台的视频。使用初始估计作为谷搜索方法或交替线搜索方法的输入来生成相机自我运动的最佳估计。所有独立的运动物体在现场使用所描述的混合方法进行检测，性能优于现有方法，同时节省了计算成本。

8. 发明申请

WO2016190928A3 SPIKE DOMAIN CONVOLUTION CIRCUIT 审中-公开
公开(公告)号：WO2016190928A3
公开(公告)日：2016-12-01
申请号：PCT/US2016/017895
申请日：2016-02-12
申请人： HRL LABORATORIES, LLC
发明人： CRUZ-ALBRECHT, Jose , YUNG, Michael, W. , SRINIVASA, Narayan
IPC分类号： G06T7/00 , G06T9/00
摘要： A convolution circuit includes: a plurality of input oscillators, each configured to: receive a corresponding analog input signal of a plurality of analog input signals; and output a corresponding spiking signal of a plurality of spiking signals, the corresponding spiking signal having a spiking rate in accordance with a magnitude of the corresponding analog input signal; a plurality of 1-bit DACs, each of the 1-bit DACs being configured to: receive the corresponding spiking signal of the plurality of spiking signals from a corresponding one of the input oscillators; and receive a corresponding weight of a convolution kernel comprising a plurality of weights; output a corresponding weighted output of a plurality of weighted outputs in accordance with the corresponding spiking signal and the corresponding weight; and an output oscillator configured to generate an output spike signal in accordance with the plurality of weighted outputs from the plurality of 1-bit DACs.

9. 发明申请

WO2014133506A1 A MIMO-OFDM SYSTEM FOR ROBUST AND EFFICIENT NEUROMORPHIC INTER-DEVICE COMMUNICATION 审中-公开
标题翻译：用于稳健和有效的神经网络设备间通信的MIMO-OFDM系统
公开(公告)号：WO2014133506A1
公开(公告)日：2014-09-04
申请号：PCT/US2013/028104
申请日：2013-02-27
申请人： HRL LABORATORIES, LLC
发明人： ZHANG, Deying , SRINIVASA, Narayan
IPC分类号： H04J11/00 , H04B7/04
CPC分类号： H04L5/0023 , G06N3/02 , G06N3/0454 , G06N3/049 , G06N3/063 , G06N3/08 , H04L27/264
摘要： A Multiple Input Multiple Output (MIMO) Orthogonal Frequency Division Multiplexing (OFDM) system for inter-device communication is described. Information data from each neuromorphic chip is coded and modulated, on the basis of destination, into different channels. The parallel signals in different channels are sent serially using TDM to a central router. After signal grouping by a central switching controller, each group of signals may be delivered to corresponding transmitter in the central router for transmission to a corresponding receiver in the neuromorphic chip using TDM.
摘要翻译：描述了用于设备间通信的多输入多输出（MIMO）正交频分复用（OFDM）系统。来自每个神经元芯片的信息数据在目的地的基础上被编码和调制成不同的信道。不同信道中的并行信号使用TDM串行发送到中央路由器。在通过中央交换控制器进行信号分组之后，可以将每组信号传送到中央路由器中的相应发射机，以使用TDM传输到神经元芯片中的相应接收机。

10. 发明申请

WO2014130120A2 GENERATING MESSAGES FROM THE FIRING OF PRE-SYNAPTIC NEURONS 审中-公开
标题翻译：从突触前神经元的发射中产生信息
公开(公告)号：WO2014130120A2
公开(公告)日：2014-08-28
申请号：PCT/US2013/072698
申请日：2013-12-02
申请人： HRL LABORATORIES, LLC
发明人： THIBEAULT, Corey, M. , MINKOVICH, Kirill , SRINIVASA, Narayan
CPC分类号： G06N3/049 , G06N3/063
摘要： A neural network portion comprising N pre-synaptic neurons capable each of firing an action potential, wherein the number N can be encoded in a word of n bits; the neural network portion providing, upon firing of a number F of pre-synaptic neurons in a predetermined period of time: if F.n N, generating a second type message, comprising N bits and encoded in words of n bits, each one of said N pre-synaptic neurons being represented by a unique bit, having a first value if the pre-synaptic neuron represented by the bit fired in said predetermined period of time, and a second value otherwise.
摘要翻译：包括N个突触前神经元的神经网络部分，每个突触前神经元能够触发动作电位，其中N可以被编码在n位的字中; 所述神经网络部分在预定时间段内发射若干F个突触前神经元时：如果F.n < N，产生第一类型消息，包括在所述预定时间周期内已经发射的每个突触前神经元的唯一地址，每个地址被编码为n位的字; 如果F.n＆gt; N，产生包括N比特并且以n比特的字编码的第二类型消息，所述N个突触前神经元中的每一个由唯一比特表示，如果由所述比特表示的突触前神经元被触发，则所述第二值具有第一值在所述预定的时间段内，并且在其他情况下为第二值。

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