ASYNCHRONOUS EARLY STOPPING IN HYPERPARAMETER METAOPTIMIZATION FOR A NEURAL NETWORK

    公开(公告)号:US20200226461A1

    公开(公告)日:2020-07-16

    申请号:US16248670

    申请日:2019-01-15

    Abstract: One embodiment of a method includes adjusting a plurality of hyperparameters corresponding to a plurality of neural networks trained asynchronously relative to each other using a plurality of computer systems. The method further includes asynchronously measuring one or more performance metrics associated with the plurality of neural networks being trained. The method further includes ceasing the adjusting of the plurality of hyperparameters corresponding to one or more of the plurality of neural networks if the one or more performance metrics associated with the one or more of the plurality of neural networks are below a threshold.

Patent Agency Ranking