You're currently viewing an old version of this dataset. To see the current version, click here.

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Training Deep Neural Networks is complicated by the fact that the distribution of each layer's inputs changes during training, as the parameters of the previous layers change.

Data and Resources

Cite this as

Sergey Ioffe, Christian Szegedy (2024). Dataset: Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. https://doi.org/10.57702/o9raffed

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Author Sergey Ioffe
More Authors
Christian Szegedy