Loading timeline…
20152010s
Sergey Ioffe
Co-invented batch normalization, which made deep networks train faster and far more reliably.
Organizations
GoogleGoogle DeepMind
Major Achievements
- •Co-authored 'Batch Normalization' (2015) with Christian Szegedy.
- •Normalising layer inputs during training cut training times sharply and reduced sensitivity to initialisation.
- •Batch normalization became a default component of convolutional architectures.
- •Contributed to the Inception line of vision models at Google.
Key Papers
- Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
Sergey Ioffe, Christian Szegedy · ICML 2015