METHOD AND APPARATUS WITH MODEL TRAINING
    1.
    发明公开

    公开(公告)号:US20240062049A1

    公开(公告)日:2024-02-22

    申请号:US18355619

    申请日:2023-07-20

    CPC classification number: G06N3/047 G06N3/08

    Abstract: A processor implemented method including iteratively training a model through repeated training operations, including calculating a respective sensitivity of each layer of plural layers included in the model, the model including a machine-learning model, calculating a first maintenance probability for a t-th repeated training of the model, calculating a respective maintenance probability of each of the plural layers of the model based on the respective sensitivity of each of the plural layers and based on the first maintenance probability for the t-th repeated training of the model, and performing the t-th repeated training of the model including training selected one or more maintenance layers, of the plural layers of the model, whose respective maintenance probabilities satisfy a first predetermined maintenance condition.

    NEURAL NETWORK MODEL QUANTIZATION METHOD AND APPARATUS

    公开(公告)号:US20220207361A1

    公开(公告)日:2022-06-30

    申请号:US17552501

    申请日:2021-12-16

    Abstract: A neural network model quantization method and apparatus is provided. The neural network model quantization method includes receiving a neural network model, calculating a quantization parameter corresponding to an operator of the neural network model to be quantized based on bisection approximation, and quantizing the operator to be quantized based on the quantization parameter and obtaining a neural network model having the quantized operator.

    BASE STATION ANTENNA AND BASE STATION

    公开(公告)号:US20210091821A1

    公开(公告)日:2021-03-25

    申请号:US17029357

    申请日:2020-09-23

    Abstract: A base station antenna and a base station including the base station antenna are provided. A base station antenna includes a transceiver array configured to output M signals, wherein M is an integer greater than 1; an antenna array including N antenna units, wherein N is an integer greater than M; a first-level signal allocating network configured to allocate first power to the M signals, and output P signals, wherein P is an integer greater than M; a signal synthesizing network including multiple signal synthesizers, wherein each of the multiple signal synthesizers utilizes two signals of the P signals to synthesize two output signals; and a second-level signal allocating network configured to allocate second power to signals output by the multiple signal synthesizers, and output N signals to the N antenna units.

Patent Agency Ranking