Machine learning accelerator
    2.
    发明授权

    公开(公告)号:US11443174B2

    公开(公告)日:2022-09-13

    申请号:US16682466

    申请日:2019-11-13

    Abstract: A neural network circuit for providing a threshold weighted sum of input signals comprises at least two arrays of transistors with programmable threshold voltage, each transistor storing a synaptic weight as a threshold voltage and having a control electrode for receiving an activation input signal. Additionally, for each array of transistors, a reference network associated therewith, which provides a reference signal to be combined with the positive or negative weight current components of the transistors of the associated array, the reference signal having opposite sign compared to the weight current components of the associated array, thereby providing the threshold of the weighted sums of the currents. Further, at least one bitline is configured to receive the combined positive and/or negative current components, each combined with their associated reference signals.

    Switching device with active portion configured to switch between insulating state and conducting state

    公开(公告)号:US10680597B2

    公开(公告)日:2020-06-09

    申请号:US16414609

    申请日:2019-05-16

    Applicant: IMEC vzw

    Abstract: The disclosed technology generally relates to a switching device and more particularly to a switching device based on an active portion capable of switching from an insulating state to a conductive state. In an aspect, a switching device comprises an active portion interposed between two electrodes and capable of switching from an insulating state to a conducting state when a voltage higher than a threshold value is applied between the two electrodes. The threshold value is lowered by a dielectric permittivity distribution which produces a concentration of electrical field at a location within the active portion. Thus, the switching device may be devoid of a third control electrode.

    Machine Learning Accelerator
    6.
    发明申请

    公开(公告)号:US20200151550A1

    公开(公告)日:2020-05-14

    申请号:US16682466

    申请日:2019-11-13

    Abstract: A neural network circuit for providing a threshold weighted sum of input signals comprises at least two arrays of transistors with programmable threshold voltage, each transistor storing a synaptic weight as a threshold voltage and having a control electrode for receiving an activation input signal. Additionally, for each array of transistors, a reference network associated therewith, which provides a reference signal to be combined with the positive or negative weight current components of the transistors of the associated array, the reference signal having opposite sign compared to the weight current components of the associated array, thereby providing the threshold of the weighted sums of the currents. Further, at least one bitline is configured to receive the combined positive and/or negative current components, each combined with their associated reference signals.

    SWITCHING DEVICE WITH ACTIVE PORTION CONFIGURED TO SWITCH BETWEEN INSULATING STATE AND CONDUCTING STATE

    公开(公告)号:US20190356308A1

    公开(公告)日:2019-11-21

    申请号:US16414609

    申请日:2019-05-16

    Applicant: IMEC vzw

    Abstract: The disclosed technology generally relates to a switching device and more particularly to a switching device based on an active portion capable of switching from an insulating state to a conductive state. In an aspect, a switching device comprises an active portion interposed between two electrodes and capable of switching from an insulating state to a conducting state when a voltage higher than a threshold value is applied between the two electrodes. The threshold value is lowered by a dielectric permittivity distribution which produces a concentration of electrical field at a location within the active portion. Thus, the switching device may be devoid of a third control electrode.

Patent Agency Ranking