Layer Normalization
Top Cited Papers
Preprint
Abstract
Training state-of-the-art, deep neural networks is computationally expensive. One way to reduce the training time is to normalize the activities of the neurons. A recently introduced technique called batch normalization uses the distribution of the summed input to a neuron over a mini-batch of training cases to compute a mean and variance which are then used to normalize the summed input to that neuron on each training case. This significantly reduces the training time in feed-forward neural networks. However, the effect of batch normalization is dependent on the mini-batch size and it is not obvious how to apply it to recurrent neural networks. In this paper, we transpose batch normalization into layer normalization by computing the mean and variance used for normalization from all of the summed inputs to the neurons in a layer on a single training case. Like batch normalization, we also give each neuron its own adaptive bias and gain which are applied after the normalization but before the non-linearity. Unlike batch normalization, layer normalization performs exactly the same computation at training and test times. It is also straightforward to apply to recurrent neural networks by computing the normalization statistics separately at each time step. Layer normalization is very effective at stabilizing the hidden state dynamics in recurrent networks. Empirically, we show that layer normalization can substantially reduce the training time compared with previously published techniques.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- ImageNet classification with deep convolutional neural networksCommunications of the ACM, 2017
- Learning Deep Structure-Preserving Image-Text Embeddings2016
- Batch normalized recurrent neural networks2016
- Aligning Books and Movies: Towards Story-Like Visual Explanations by Watching Movies and Reading Books2015
- Microsoft COCO: Common Objects in Context2014
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014
- SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- IAM-OnDB - an on-line English sentence database acquired from handwritten text on a whiteboard2005
- Natural Gradient Works Efficiently in LearningNeural Computation, 1998