Neural network training device, system and method

    公开(公告)号:US11501424B2

    公开(公告)日:2022-11-15

    申请号:US16687345

    申请日:2019-11-18

    Inventor: Laurent Bidault

    Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on the digital image representation of the WDM and a data-driven model generated using an artificial wafer defect digital image (AWDI) data set and associating AWDIs with classes of a defined set of classes of wafer defects. A wafer manufacturing process may be controlled based on the classifications of WDMs.

    Neural network training device, system and method

    公开(公告)号:US11200659B2

    公开(公告)日:2021-12-14

    申请号:US16687349

    申请日:2019-11-18

    Inventor: Laurent Bidault

    Abstract: A device includes image generation circuitry and convolutional-neural-network circuitry. The image generation circuitry, in operation, generates a digital image representation of a wafer defect map (WDM). The convolutional-neural-network circuitry, in operation, generates a defect classification associated with the WDM based on: the digital image representation of the WDM and a data-driven model associating WDM images with classes of a defined set of classes of wafer defects and generated using a training data set augmented based on defect pattern orientation types associated with training images.

Patent Agency Ranking