ANTI-REFLECTIVE NANOSTRUCTURE AND METHOD OF MANUFACTURING THE SAME

    公开(公告)号:US20240339548A1

    公开(公告)日:2024-10-10

    申请号:US18628296

    申请日:2024-04-05

    IPC分类号: H01L31/0236

    CPC分类号: H01L31/02363

    摘要: The present disclosure relates to an anti-reflective nanostructure and a method of manufacturing the same, and more particularly, to an anti-reflective nanostructure having a refractive index close to a quintic refractive index profile and exhibiting an anti-reflection effect in which a reflectance is close to almost 0.
    The anti-reflective nanostructure according to an embodiment of the present invention includes: a base part having a top surface; and a plurality of nanostructures arranged in a first direction on the top surface and each having a shape in which an upper portion has a thin and sharp shape, a lower portion has a width greater than that of the upper portion, and the width gradually increases in a direction from the upper portion to the lower portion.

    Method and apparatus with neural network data quantizing

    公开(公告)号:US12106219B2

    公开(公告)日:2024-10-01

    申请号:US15931362

    申请日:2020-05-13

    IPC分类号: G06N3/084 G06N3/04 G06N3/0495

    CPC分类号: G06N3/084 G06N3/04 G06N3/0495

    摘要: A neural network data quantizing method includes: obtaining local quantization data by firstly quantizing, based on a local maximum value for each output channel of a current layer of a neural network, global recovery data obtained by recovering output data of an operation of the current layer based on a global maximum value corresponding to a previous layer of the neural network; storing the local quantization data in a memory to perform an operation of a next layer of the neural network; obtaining global quantization data by secondarily quantizing, based on a global maximum value corresponding to the current layer, local recovery data obtained by recovering the local quantization data based on the local maximum value for each output channel of the current layer; and providing the global quantization data as input data for the operation of the next layer.