中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

8 records (took 0.012 seconds)

    SYSTEM AND METHOD FOR DECODING SPIKING RESERVOIRS WITH CONTINUOUS SYNAPTIC PLASTICITY
    3.
    发明申请
    SYSTEM AND METHOD FOR DECODING SPIKING RESERVOIRS WITH CONTINUOUS SYNAPTIC PLASTICITY 审中-公开

    公开(公告)号：US20170316310A1

    公开(公告)日：2017-11-02

    申请号：US15075063

    申请日：2016-03-18

    Applicant: HRL Laboratories, LLC

    Inventor： Youngkwan Cho ,  Narayan Srinivasa

    IPC: G06N3/08

    CPC classification number: G06N3/08 ,  G01S7/414 ,  G01S7/417 ,  G06K9/00543 ,  G06K9/00805 ,  G06K9/4623 ,  G06K9/66 ,  G06N3/0445 ,  G06N3/049 ,  G06N3/088

    Abstract: Described is a system for decoding spiking reservoirs even when the spiking reservoir has continuous synaptic plasticity. The system uses a set of training patterns to train a neural network having a spiking reservoir comprised of spiking neurons. A test pattern duration d is estimated for a set of test patterns P, and each test pattern is presented to the spiking reservoir for a duration of d/P seconds. Output spikes from the spiking reservoir are generated via readout neurons. The output spikes are measured and the measurements are used to compute firing rate codes, each firing rate code corresponding to a test pattern in the set of test patterns P. The firing rate codes are used to decode performance of the neural network by computing a discriminability index (DI) to discriminate between test patterns in the set of test patterns P.

    METHOD OF REAL TIME VEHICLE RECOGNITION WITH NEUROMORPHIC COMPUTING NETWORK FOR AUTONOMOUS DRIVING
    4.
    发明申请
    METHOD OF REAL TIME VEHICLE RECOGNITION WITH NEUROMORPHIC COMPUTING NETWORK FOR AUTONOMOUS DRIVING 审中-公开

    公开(公告)号：US20200026287A1

    公开(公告)日：2020-01-23

    申请号：US16519814

    申请日：2019-07-23

    Applicant: HRL Laboratories, LLC

    Inventor： Qin Jiang ,  Youngkwan Cho ,  Nigel D. Stepp ,  Steven W. Skorheim ,  Vincent De Sapio ,  Praveen K. Pilly ,  Ruggero Scorcioni

    IPC: G05D1/00 ,  G05B13/02 ,  G05D1/02

    Abstract: Described is a system for online vehicle recognition in an autonomous driving environment. Using a learning network comprising an unsupervised learning component and a supervised learning component, images of moving vehicles extracted from videos captured in the autonomous driving environment are learned and classified. Vehicle feature data is extracted from input moving vehicle images. The extracted vehicle feature data is clustered into different vehicle classes using the unsupervised learning component. Vehicle class labels for the different vehicle classes are generated using the supervised learning component. Based on a vehicle class label for a moving vehicle in the autonomous driving environment, the system selects an action to be performed by the autonomous vehicle, and causes the selected action to be performed by the autonomous vehicle in the autonomous driving environment.

    SPIKING MODEL TO LEARN ARBITRARY MULTIPLE TRANSFORMATIONS FOR A SELF-REALIZING NETWORK
    5.
    发明申请
    SPIKING MODEL TO LEARN ARBITRARY MULTIPLE TRANSFORMATIONS FOR A SELF-REALIZING NETWORK 有权
    用于实现自动实现网络的ARKITARY多种变换的SPIKEING模型

    公开(公告)号：US20150026110A1

    公开(公告)日：2015-01-22

    申请号：US14015001

    申请日：2013-08-30

    Applicant: HRL LABORATORIES, LLC

    Inventor： Narayan Srinivasa ,  Youngkwan Cho

    IPC: G06N3/08

    CPC classification number: G06N3/08 ,  G06N3/049

    Abstract: 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.

    Abstract translation: 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枝晶形成与第二阵列的相邻神经元的轴突的兴奋性STDP突触。

    System and method for decoding spiking reservoirs with continuous synaptic plasticity
    7.
    发明授权
    System and method for decoding spiking reservoirs with continuous synaptic plasticity 有权

    公开(公告)号：US10586150B2

    公开(公告)日：2020-03-10

    申请号：US15075063

    申请日：2016-03-18

    Applicant: HRL Laboratories, LLC

    Inventor： Youngkwan Cho ,  Narayan Srinivasa

    IPC: G06N3/08 ,  G06K9/00 ,  G06K9/66 ,  G06K9/46 ,  G06N3/04 ,  G01S7/41

    Abstract: Described is a system for decoding spiking reservoirs even when the spiking reservoir has continuous synaptic plasticity. The system uses a set of training patterns to train a neural network having a spiking reservoir comprised of spiking neurons. A test pattern duration d is estimated for a set of test patterns P, and each test pattern is presented to the spiking reservoir for a duration of d/P seconds. Output spikes from the spiking reservoir are generated via readout neurons. The output spikes are measured and the measurements are used to compute firing rate codes, each firing rate code corresponding to a test pattern in the set of test patterns P. The firing rate codes are used to decode performance of the neural network by computing a discriminability index (DI) to discriminate between test patterns in the set of test patterns P.

    Spiking model to learn arbitrary multiple transformations for a self-realizing network
    8.
    发明授权
    Spiking model to learn arbitrary multiple transformations for a self-realizing network 有权
    Spiking模型为自我实现网络学习任意多变量

    公开(公告)号：US09430737B2

    公开(公告)日：2016-08-30

    申请号：US14015001

    申请日：2013-08-30

    Applicant: HRL LABORATORIES, LLC

    Inventor： Narayan Srinivasa ,  Youngkwan Cho

    IPC: G06N3/08 ,  G06N3/04

    CPC classification number: G06N3/08 ,  G06N3/049

    Abstract: 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.

    Abstract translation: 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枝晶形成与第二阵列的相邻神经元的轴突的兴奋性STDP突触。

Patent Agency Ranking