Translations:Batch Normalization Accelerating Deep Network Training/20/en: Difference between revisions

    From Marovi AI
    (Importing a new version from external source)
     
    (Importing a new version from external source)
     
    Line 1: Line 1:
    * A batch-normalized network matched the accuracy of the original Inception model in only '''7% of the training steps''' (14x acceleration).
    * A batch-normalized network matched the accuracy of the original Inception model in only '''7% of the training steps''' (14x acceleration).
    * '''BN-Inception''' (with batch normalization and other modifications) achieved a top-5 validation error of 4.82%, exceeding the accuracy of the original GoogLeNet (6.67%) and approaching human performance.
    * '''BN-Inception''' (with {{Term|batch normalization}} and other modifications) achieved a top-5 validation error of 4.82%, exceeding the accuracy of the original GoogLeNet (6.67%) and approaching human performance.
    * Using batch normalization allowed training with a learning rate 10x higher than the baseline without divergence.
    * Using {{Term|batch normalization}} allowed training with a {{Term|learning rate}} 10x higher than the baseline without divergence.
    * On some configurations, batch normalization eliminated the need for dropout without accuracy loss, simplifying the architecture and reducing training time further.
    * On some configurations, {{Term|batch normalization}} eliminated the need for {{Term|dropout}} without accuracy loss, simplifying the architecture and reducing training time further.

    Latest revision as of 21:40, 27 April 2026

    Information about message (contribute)
    This message has no documentation. If you know where or how this message is used, you can help other translators by adding documentation to this message.
    Message definition (Batch Normalization Accelerating Deep Network Training)
    * A batch-normalized network matched the accuracy of the original Inception model in only '''7% of the training steps''' (14x acceleration).
    * '''BN-Inception''' (with {{Term|batch normalization}} and other modifications) achieved a top-5 validation error of 4.82%, exceeding the accuracy of the original GoogLeNet (6.67%) and approaching human performance.
    * Using {{Term|batch normalization}} allowed training with a {{Term|learning rate}} 10x higher than the baseline without divergence.
    * On some configurations, {{Term|batch normalization}} eliminated the need for {{Term|dropout}} without accuracy loss, simplifying the architecture and reducing training time further.
    • A batch-normalized network matched the accuracy of the original Inception model in only 7% of the training steps (14x acceleration).
    • BN-Inception (with batch normalization and other modifications) achieved a top-5 validation error of 4.82%, exceeding the accuracy of the original GoogLeNet (6.67%) and approaching human performance.
    • Using batch normalization allowed training with a learning rate 10x higher than the baseline without divergence.
    • On some configurations, batch normalization eliminated the need for dropout without accuracy loss, simplifying the architecture and reducing training time further.