Oscillator based neural network apparatus

    公开(公告)号:US12020144B2

    公开(公告)日:2024-06-25

    申请号:US16579765

    申请日:2019-09-23

    申请人: Intel Corporation

    IPC分类号: G06N3/065 G06N3/048 H03M1/66

    CPC分类号: G06N3/065 G06N3/048 H03M1/66

    摘要: A neural network scheme is described that uses unsupervised learning in oscillator neural networks. Training occurs by varying the weights in proportion to the output from a frequency detector. Inputs and initial weights are split into plurality of inputs and plurality of weights. These split inputs and weights can be analog or digital. Oscillators generate signals having frequencies that represent difference in inputs, initial weights, and adjusted factors. Frequency detectors are used to compare the oscillator frequencies with a synchronized frequency of all oscillators. The output of the frequency detectors are used to generate the adjusted factors, and in turn generate trained weights.

    Visual query language for code review rules

    公开(公告)号:US12007877B1

    公开(公告)日:2024-06-11

    申请号:US17708269

    申请日:2022-03-30

    IPC分类号: G06F9/44 G06F11/36

    CPC分类号: G06F11/3664 G06F11/3688

    摘要: Techniques for providing a visual code review editor are described. An electronic device is caused to display a graphical user interface including an editor portion to edit code review rules used by a code review service of a cloud provider network. The editor portion of the graphical user interface is caused to display a first graph associated with a first code review rule, the first graph including a first node, a second node, and a first edge connecting the first node and the second node. An indication that a third node has been added to the graph via the editor portion of the graphical user interface is received. The first code review rule is updated by the code review service to reflect the addition of the third node, the first code review rule is in a text format.