利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

17 条记录 (耗时 0.016 秒)

    HANDLING SIGNAL SATURATION IN SPIKING NEURAL NETWORKS
    2.
    发明申请
    HANDLING SIGNAL SATURATION IN SPIKING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20180276529A1

    公开(公告)日：2018-09-27

    申请号：US15468838

    申请日：2017-03-24

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Narayan Srinivasa

    IPC分类号： G06N3/04 ,  G06N3/08

    CPC分类号： G06N3/049 ,  G06N3/0454

    摘要： The present disclosure provides for generating a spiking neural network. Generating a spiking neural network can include determining that a first input fan-in from a plurality of input neurons to each of a plurality of output neurons is greater than a threshold, generating a plurality of intermediate neurons based on a determination that the first input fan-in is greater than the threshold, and coupling the plurality of intermediate neurons to the plurality of input neurons and the plurality of output neurons, wherein each of the plurality of intermediate neurons has a second input fan-in that is less than the first input fan-in and each of the plurality of output neurons has a third input fan-in that is less than the first input fan-in.

    Device, system and method for varying a synaptic weight with a phase differential of a spiking neural network
    3.
    发明授权
    Device, system and method for varying a synaptic weight with a phase differential of a spiking neural network 有权

    公开(公告)号：US11568241B2

    公开(公告)日：2023-01-31

    申请号：US16648437

    申请日：2017-12-19

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Narayan Srinivasa

    IPC分类号： G06N3/08 ,  G06N3/04

    摘要： Techniques and mechanisms for determining the value of a weight associated with a synapse of a spiking neural network. In an embodiment, a first spike train and a second spike train are output, respectively, by a first node and a second node of the spiking neural network, wherein the synapse is coupled between said nodes. The weight is applied to signaling communicated via the synapse. A value of the weight is updated based on a product of a first value and a second value, wherein the first value is based on a first rate of spiking by the first spike train, and the second value is based on a second rate of spiking by the second spike train. In another embodiment, the weight is updated based on a product of a derivative of the first rate of spiking and a derivative of the second rate of spiking.

    Reconstruction of signals using a Gramian Matrix
    6.
    发明申请
    Reconstruction of signals using a Gramian Matrix 审中-公开

    公开(公告)号：US20170185900A1

    公开(公告)日：2017-06-29

    申请号：US14998235

    申请日：2015-12-26

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Nilesh Jain ,  Hsiang-Tsung Kung

    IPC分类号： G06N5/02 ,  G06F17/27 ,  G06N99/00

    CPC分类号： G06N20/00

    摘要： An apparatus is described herein. The apparatus includes a clustering mechanism that is to partition a dictionary into a plurality of clusters. The apparatus also includes a feature-matching mechanism that is to pre-compute feature matching results for each cluster of the plurality of clusters. Moreover, the apparatus includes a selector that is to locate a best representative feature from the dictionary in response to an input vector.

    Context-based search using spike waves in spiking neural networks
    7.
    发明授权
    Context-based search using spike waves in spiking neural networks 有权

    公开(公告)号：US11636318B2

    公开(公告)日：2023-04-25

    申请号：US16647814

    申请日：2017-12-15

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Narayan Srinivasa

    IPC分类号： G06N3/04 ,  G06N3/049

    摘要： Techniques and mechanisms for servicing a search query using a spiking neural network. In an embodiment, a spiking neural network receives an indication of a first context of the search query, wherein a set of nodes of the spiking neural network each correspond to a respective entry of a repository. One or more nodes of the set of nodes are each excited to provide a respective cyclical response based on the first context, wherein a first cyclical response is by a first node. Due at least in part to a coupling of the excited nodes, a perturbance signal, based on a second context of the search query, results in a change of the first resonance response relative to one or more other resonance responses. In another embodiment, data corresponding to the first node is selected, based on the change, as an at least partial result of the search query.

    Handling signal saturation in spiking neural networks
    8.
    发明授权
    Handling signal saturation in spiking neural networks 有权

    公开(公告)号：US10679119B2

    公开(公告)日：2020-06-09

    申请号：US15468838

    申请日：2017-03-24

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Narayan Srinivasa

    IPC分类号： G06N3/04

    摘要： The present disclosure provides for generating a spiking neural network. Generating a spiking neural network can include determining that a first input fan-in from a plurality of input neurons to each of a plurality of output neurons is greater than a threshold, generating a plurality of intermediate neurons based on a determination that the first input fan-in is greater than the threshold, and coupling the plurality of intermediate neurons to the plurality of input neurons and the plurality of output neurons, wherein each of the plurality of intermediate neurons has a second input fan-in that is less than the first input fan-in and each of the plurality of output neurons has a third input fan-in that is less than the first input fan-in.

    OBJECT RECOGNITION USING A SPIKING NEURAL NETWORK
    9.
    发明申请
    OBJECT RECOGNITION USING A SPIKING NEURAL NETWORK 审中-公开

    公开(公告)号：US20180276530A1

    公开(公告)日：2018-09-27

    申请号：US15468881

    申请日：2017-03-24

    申请人： INTEL CORPORATION

    发明人： Arnab Paul ,  Narayan Srinivasa

    IPC分类号： G06N3/04 ,  G06N3/08

    CPC分类号： G06N3/049 ,  G06N3/08 ,  G06N3/088

    摘要： Embodiments described herein describe object recognition using a spiking neural network. Object recognition using a spiking neural network can include processing each of the plurality of base templates through a plurality of input neurons to generate a plurality of first spikes through the plurality of input neurons, providing the plurality of first spikes from the plurality of input neurons to each of a plurality of excitatory neurons (E-neurons), providing a plurality of second spikes from a plurality of inhibitory neurons (I-neurons) to the plurality of E-neurons to inhibit a spiking rate of the E-neurons, generating a plurality of weights at each of the plurality of E-neurons based on the plurality of first spikes and the plurality of second spikes, and classifying a pattern utilizing the plurality of input neurons, the plurality of E-neurons, and the plurality of weights at each of the E-neurons.