中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

17 records (took 0.017 seconds)

    Parsing regular expressions with spiking neural networks
    11.
    发明授权
    Parsing regular expressions with spiking neural networks 有权

    公开(公告)号：US11663449B2

    公开(公告)日：2023-05-30

    申请号：US16648169

    申请日：2017-12-15

    Applicant: Intel Corporation

    Inventor： Arnab Paul ,  Narayan Srinivasa

    IPC: G06F16/00 ,  G06N3/049 ,  G06N3/08

    CPC classification number: G06N3/049 ,  G06N3/08

    Abstract: Techniques and mechanisms for providing a logical state machine with a spiking neural network which includes multiple sets of nodes. Each of the multiple sets of nodes is to implement a different respective state, and each of the multiple spike trains is provided to respective nodes of each of the multiple sets of nodes. A given state of the logical state machine is implemented by configuring respective activation modes of each node of the corresponding set of nodes. The activation mode of a given node enables that node to signal, responsive to its corresponding spike train, that a respective state transition of the logical state machine is to be performed. In another embodiment, the multiple spike trains each represent a different respective character in a system used by data evaluated with the spiking neural network.

    Method, device and system to generate a Bayesian inference with a spiking neural network
    12.
    发明授权
    Method, device and system to generate a Bayesian inference with a spiking neural network 有权

    公开(公告)号：US11544564B2

    公开(公告)日：2023-01-03

    申请号：US16957056

    申请日：2018-02-23

    Applicant: Intel Corporation

    Inventor： Arnab Paul ,  Narayan Srinivasa

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Techniques and mechanisms for performing a Bayesian inference with a spiking neural network. In an embodiment, a parent node of the spiking neural network receives a first bias signal which is periodic. The parent node communicates a likelihood signal to a child node, wherein the parent node and the child node correspond to a first condition and a second condition, respectively. Based on a phase change which is applied to the first bias signal, the likelihood signal indicates a probability of the first condition. The child node also receives a signal which indicates an instance of the second condition. Based on the indication and a second bias signal, the child node signals to the first node that an adjustment is to be made to the phase change applied to the first bias signal. After the adjustment, the likelihood signal indicates an updated probability of the first condition.

    METHOD, DEVICE AND SYSTEM TO GENERATE A BAYESIAN INFERENCE WITH A SPIKING NEURAL NETWORK
    15.
    发明申请
    METHOD, DEVICE AND SYSTEM TO GENERATE A BAYESIAN INFERENCE WITH A SPIKING NEURAL NETWORK 审中-公开

    公开(公告)号：US20200342321A1

    公开(公告)日：2020-10-29

    申请号：US16957056

    申请日：2018-02-23

    Applicant: Intel Corporation

    Inventor： Arnab Paul ,  Narayan Srinivasa

    IPC: G06N3/08 ,  G06N3/04

    Abstract: Techniques and mechanisms for performing a Bayesian inference with a spiking neural network. In an embodiment, a parent node of the spiking neural network receives a first bias signal which is periodic. The parent node communicates a likelihood signal to a child node, wherein the parent node and the child node correspond to a first condition and a second condition, respectively. Based on a phase change which is applied to the first bias signal, the likelihood signal indicates a probability of the first condition. The child node also receives a signal which indicates an instance of the second condition. Based on the indication and a second bias signal, the child node signals to the first node that an adjustment is to be made to the phase change applied to the first bias signal. After the adjustment, the likelihood signal indicates an updated probability of the first condition.

    PARSING REGULAR EXPRESSIONS WITH SPIKING NEURAL NETWORKS
    16.
    发明申请
    PARSING REGULAR EXPRESSIONS WITH SPIKING NEURAL NETWORKS 审中-公开

    公开(公告)号：US20200265290A1

    公开(公告)日：2020-08-20

    申请号：US16648169

    申请日：2017-12-15

    Applicant: Intel Corporation

    Inventor： Arnab Paul ,  Narayan Srinivasa

    IPC: G06N3/04 ,  G06N3/08

    Abstract: Techniques and mechanisms for providing a logical state machine with a spiking neural network which includes multiple sets of nodes. Each of the multiple sets of nodes is to implement a different respective state, and each of the multiple spike trains is provided to respective nodes of each of the multiple sets of nodes. A given state of the logical state machine is implemented by configuring respective activation modes of each node of the corresponding set of nodes. The activation mode of a given node enables that node to signal, responsive to its corresponding spike train, that a respective state transition of the logical state machine is to be performed. In another embodiment, the multiple spike trains each represent a different respective character in a system used by data evaluated with the spiking neural network.

Patent Agency Ranking