2015 BatchNormalizationAcceleratingD

• (Ioffe & Szegedy, 2015) ⇒ Sergey Ioffe, and Christian Szegedy. (2015). “Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift.” In: Proceedings of the 32nd International Conference on Machine Learning (ICML 2015)..

Subject Headings: Batch Normalization-Based NNet Algorithm; Batch Normalization.

Cited By

• http://scholar.google.com/scholar?q=%222015%22+Batch+Normalization%3A+Accelerating+Deep+Network+Training+by+Reducing+Internal+Covariate+Shift

Quotes

Abstract

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. This slows down the training by requiring lower learning rates and careful parameter initialization, and makes it notoriously hard to train models with saturating nonlinearities. We refer to this phenomenon as internal covariate shift, and address the problem by normalizing layer inputs. Our method draws its strength from making normalization a part of the model architecture and performing the normalization for each training mini-batch. Batch Normalization allows us to use much higher learning rates and be less careful about initialization, and in some cases eliminates the need for Dropout. Applied to a stateof-the-art image classification model, Batch Normalization achieves the same accuracy with 14 times fewer training steps, and beats the original model by a significant margin. Using an ensemble of batch-normalized networks, we improve upon the best published result on ImageNet classification: reaching 4.82% top-5 test error, exceeding the accuracy of human raters.

BibTeX

@inproceedings{2015_BatchNormalizationAcceleratingD,
  author    = {Sergey Ioffe and
               Christian Szegedy},
  editor    = {Francis R. Bach and
 [[David M. Blei]]},
  title     = {Batch Normalization: Accelerating Deep Network Training by Reducing
               Internal Covariate Shift},
  booktitle = {Proceedings of the 32nd International Conference on Machine Learning,
               (ICML 2015)},
  series    = {JMLR Workshop and Conference Proceedings},
  volume    = {37},
  pages     = {448--456},
  publisher = {JMLR.org},
  year      = {2015},
  url       = {http://proceedings.mlr.press/v37/ioffe15.html},
}

---

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2015 BatchNormalizationAcceleratingD	Christian Szegedy Sergey Ioffe			Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift						2015