Enhanced precision machine learning prediction

    公开(公告)号:US12106189B2

    公开(公告)日:2024-10-01

    申请号:US17087935

    申请日:2020-11-03

    Abstract: Training a machine learning model includes electronically retrieving feature vectors that comprise a electronic representations of multidimensional observations, each observation uniquely associated with a predetermined observation value. A multi-class data structure comprising a plurality of buckets is generated by binning the observation values associated with the multidimensional observations. Each bucket corresponds to a range of values and contains observations whose associated observation values lie within the range. A machine learning model is trained using the feature vectors to classify feature vector inputs, assigning each feature vector input to a bucket. Simulated execution of the machine learning model classifies simulation feature vectors by assigning each simulation feature vector to a bucket based on the feature. For each bucket, a regression value is determined based on an aggregation of simulation feature vectors assigned to the bucket, thereby enabling the machine learning model to predict regression values corresponding to subsequent feature vector inputs.

    ENHANCED PRECISION MACHINE LEARNING PREDICTION

    公开(公告)号:US20220138618A1

    公开(公告)日:2022-05-05

    申请号:US17087935

    申请日:2020-11-03

    Abstract: Training a machine learning model includes electronically retrieving feature vectors that comprise a electronic representations of multidimensional observations, each observation uniquely associated with a predetermined observation value. A multi-class data structure comprising a plurality of buckets is generated by binning the observation values associated with the multidimensional observations. Each bucket corresponds to a range of values and contains observations whose associated observation values lie within the range. A machine learning model is trained using the feature vectors to classify feature vector inputs, assigning each feature vector input to a bucket. Simulated execution of the machine learning model classifies simulation feature vectors by assigning each simulation feature vector to a bucket based on the feature. For each bucket, a regression value is determined based on an aggregation of simulation feature vectors assigned to the bucket, thereby enabling the machine learning model to predict regression values corresponding to subsequent feature vector inputs.

    Substrate processing apparatus
    10.
    发明授权

    公开(公告)号:US12298676B2

    公开(公告)日:2025-05-13

    申请号:US18322161

    申请日:2023-05-23

    Abstract: A substrate processing apparatus includes a table in an exposure chamber that is configured to perform an exposure process on a semiconductor substrate, a guiding device including a first horizontal driving body slidably movable in a first horizontal direction and a guide rail on the first horizontal driving body and having a trench extending in a second horizontal direction, a positioning device connected to the guiding device, the positioning device including a slider, a second horizontal driving body and a substrate stage, the slider configured to slidably move in the second horizontal direction along the trench, the second horizontal driving body connected or fixed to the slider, the substrate stage on the second horizontal driving body and configured to support the semiconductor substrate, and a blocking member between the guide rail and the substrate stage to block an inflow of foreign substances onto the substrate stage.

Patent Agency Ranking