MULTI-STAGE TRAINING OF MACHINE LEARNING MODELS

    公开(公告)号:US20230259769A1

    公开(公告)日:2023-08-17

    申请号:US18168027

    申请日:2023-02-13

    CPC classification number: G06N3/08

    Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a machine learning model to perform a machine learning task. In one aspect, a method includes: obtaining a set of training examples; obtaining, for each training example, a respective metadata label that characterizes the training example; and training the machine learning model over a sequence of training stages, including, at each training stage: identifying a selection criterion corresponding to the current training stage that defines a criterion for selecting training examples based on the metadata labels of the training examples; selecting a proper subset of the set training examples as training data for the current training stage in accordance with the selection criterion for the current training stage; and updating the machine learning model by training the machine learning model on the training data for the current training stage.

Patent Agency Ranking