paper-with-me

홈 › Papers

Generalized Batch Normalization: Towards Accelerating Deep Neural Networks

2018-12-08 · Xiaoyong Yuan, Zheng Feng, Matthew Norton, Xiaolin Li

Utilizing recently introduced concepts from statistics and quantitative risk management, we present a general variant of Batch Normalization (BN) that offers accelerated convergence of Neural Network training compared to conventional BN. In general, we show that mean and standard deviation are not always the most appropriate choice for the centering and scaling procedure within the BN transformation, particularly if ReLU follows the normalization step. We present a Generalized Batch Normalization (GBN) transformation, which can utilize a variety of alternative deviation measures for scaling and statistics for centering, choices which naturally arise from the theory of generalized deviation measures and risk theory in general. When used in conjunction with the ReLU non-linearity, the underlying risk theory suggests natural, arguably optimal choices for the deviation measure and statistic. Utilizing the suggested deviation measure and statistic, we show experimentally that training is accelerated more so than with conventional BN, often with improved error rate as well. Overall, we propose a more flexible BN transformation supported by a complimentary theoretical framework that can potentially guide design choices.

📄 PDF Abstract BibTeX arXiv:1812.03271

Code (0)

등록된 구현이 없습니다.

Tasks

Management

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Kalman Normalization: Normalizing Internal Representations Across Network Layers

2018-12-01 · NeurIPS 2018 12 · Guangrun Wang, Jiefeng Peng, Ping Luo, Xinjiang Wang 외

As an indispensable component, Batch Normalization (BN) has successfully improved the training of deep neural networks (DNNs) with mini-batches, by normalizing the distribution of the internal representation for each hid…

object-detectionObject Detection

Diminishing Batch Normalization

2017-05-22 · ICLR 2019 5 · Yintai Ma, Diego Klabjan

In this paper, we propose a generalization of the Batch Normalization (BN) algorithm, diminishing batch normalization (DBN), where we update the BN parameters in a diminishing moving average way. BN is very effective in …

Batch Renormalization: Towards Reducing Minibatch Dependence in Batch-Normalized Models

2017-02-10 · NeurIPS 2017 12 · Sergey Ioffe

Batch Normalization is quite effective at accelerating and improving the training of deep models. However, its effectiveness diminishes when the training minibatches are small, or do not consist of independent samples. W…

Accelerating Training of Deep Neural Networks with a Standardization Loss

2019-03-03 · Jasmine Collins, Johannes Balle, Jonathon Shlens

A significant advance in accelerating neural network training has been the development of normalization methods, permitting the training of deep models both faster and with better accuracy. These advances come with pract…

image-classificationImage Classification

POP-Norm: A Theoretically Justified and More Accelerated Normalization Approach

2019-09-25 · Hanyang Peng, Shiqi Yu

Batch Normalization (BatchNorm) has been a default module in modern deep networks due to its effectiveness for accelerating training deep neural networks. It is widely accepted that the great success of BatchNorm is o…