Pop count-based deep learning neural network computation method, multiply accumulator and device

    公开(公告)号:US12260188B2

    公开(公告)日:2025-03-25

    申请号:US17254254

    申请日:2020-11-30

    Abstract: The present invention relates to a pop count-based deep learning neural network computation method, a multiply accumulator, and a device thereof. The computation method according to an exemplary embodiment of the present invention is a computation method for a deep learning neural network, including a step of generating one-hot encoding codes according to the type of first multiplication result values for a multiplication (first multiplication) of weights (W) and input values (A); a step of performing a pop-count for each generated code; and a step of accumulating result values for a constant multiplication (second multiplication) between each type of the first multiplication result value and each count value of the pop-count which are different constant values.

    System for wireless power transmission

    公开(公告)号:US11264843B1

    公开(公告)日:2022-03-01

    申请号:US17127419

    申请日:2020-12-18

    Abstract: The present invention provides a system tar wireless power transmission, wherein the system is a system for wireless power transmission detecting a foreign object, including a power transmitting coil for transmitting AC power, a power receiving coil for receiving the AC power transmitted from the power transmitting coil wherein the power receiving coil is spaced apart from the power transmitting coil, and a detection circuit for detecting a foreign object located between the power transmitting coil and the power receiving coil wherein a first resistor and a first detection coil connected in series, and a second resistor and a second detection coil connected in series are connected in parallel, and wherein at least one of the first detection coil and the second detection coil is disposed between the power transmitting coil and the power receiving coil.

Patent Agency Ranking