arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1502.03167cs.LG
收藏

批量归一化:通过减少内部协变量偏移来加速深度网络训练

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

Google Inc.(谷歌公司)

Sergey Ioffe, Christian Szegedy

摘要:

训练深度神经网络是复杂的,因为在训练过程中,随着前一层的参数变化,每层输入的分布都会发生变化。这就需要较低的学习率和仔细的参数初始化,从而减慢了训练速度,并且使得训练具有饱和非线性的模型变得非常困难。我们将这种现象称为内部协变量偏移,并通过规范化层输入来解决这个问题。我们的方法将标准化作为模型架构的一部分,并为每个训练小批量执行标准化。批量归一化使我们能够使用更高的学习率,并且不必太小心初始化。它还充当正则化器,在某些情况下消除了对Dropout的需要。应用于最先进的图像分类模型,批量归一化实现了相同的准确性,训练步骤减少了14倍,并大大超过了原始模型。使用批量归一化网络的集合,我们改进了ImageNet分类的最佳结果:达到4.9%的前5名验证错误(和4.8%的测试错误),超过了人类评分员的准确性。

英文摘要:

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. It also acts as a regularizer, in some cases eliminating the need for Dropout. Applied to a state-of-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 4.9% top-5 validation error (and 4.8% test error), exceeding the accuracy of human raters.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑