摘要翻译：
正则化对于许多实际的深度学习模型的成功至关重要，尤其是在只有少数到中等数量的可访问训练样本的情况下。除了权值衰减、数据增加和丢失之外，基于多分支结构的正则化，如Shake-Shake正则化，已经在许多应用中被证明是成功的，并受到越来越多的关注。然而，除了基于模型的表示增强之外，尚不清楚抖动-抖动正则化如何帮助进一步改进分类任务，更不用说成批归一化和抖动之间令人困惑的相互作用了。在这项工作中，我们提出了我们对抖抖正则化的研究，并将其与邻近风险最小化原则和验证任务中的鉴别特征学习联系起来。此外，我们发现批归一化残差块和批归一化递归神经网络之间有很强的相似性，它们都有相似的收敛行为，这可以通过适当的批归一化初始化来缓解。在此基础上，我们对语音情感识别的实验表明，同时提高了分类精度和减少了泛化差距，两者都具有统计学意义。
---
英文标题：
《Normalization Before Shaking Toward Learning Symmetrically Distributed
  Representation Without Margin in Speech Emotion Recognition》
---
作者：
Che-Wei Huang and Shrikanth S. Narayanan
---
最新提交年份：
2018
---
分类信息：

一级分类：Computer Science        计算机科学
二级分类：Machine Learning        机器学习
分类描述：Papers on all aspects of machine learning research (supervised, unsupervised, reinforcement learning, bandit problems, and so on) including also robustness, explanation, fairness, and methodology. cs.LG is also an appropriate primary category for applications of machine learning methods.
关于机器学习研究的所有方面的论文（有监督的，无监督的，强化学习，强盗问题，等等），包括健壮性，解释性，公平性和方法论。对于机器学习方法的应用，CS.LG也是一个合适的主要类别。
--
一级分类：Computer Science        计算机科学
二级分类：Human-Computer Interaction        人机交互
分类描述：Covers human factors, user interfaces, and collaborative computing. Roughly includes material in ACM Subject Classes H.1.2 and all of H.5, except for H.5.1, which is more likely to have Multimedia as the primary subject area.
包括人为因素、用户界面和协作计算。大致包括ACM学科课程H.1.2和所有H.5中的材料，除了H.5.1，它更有可能以多媒体作为主要学科领域。
--
一级分类：Computer Science        计算机科学
二级分类：Multimedia        多媒体
分类描述：Roughly includes material in ACM Subject Class H.5.1.
大致包括ACM学科类H.5.1中的材料。
--
一级分类：Computer Science        计算机科学
二级分类：Sound        声音
分类描述：Covers all aspects of computing with sound, and sound as an information channel. Includes models of sound, analysis and synthesis, audio user interfaces, sonification of data, computer music, and sound signal processing. Includes ACM Subject Class H.5.5, and intersects with H.1.2, H.5.1, H.5.2, I.2.7, I.5.4, I.6.3, J.5, K.4.2.
涵盖了声音计算的各个方面，以及声音作为一种信息通道。包括声音模型、分析和合成、音频用户界面、数据的可听化、计算机音乐和声音信号处理。包括ACM学科类H.5.5，并与H.1.2、H.5.1、H.5.2、I.2.7、I.5.4、I.6.3、J.5、K.4.2交叉。
--
一级分类：Electrical Engineering and Systems Science        电气工程与系统科学
二级分类：Audio and Speech Processing        音频和语音处理
分类描述：Theory and methods for processing signals representing audio, speech, and language, and their applications. This includes analysis, synthesis, enhancement, transformation, classification and interpretation of such signals as well as the design, development, and evaluation of associated signal processing systems. Machine learning and pattern analysis applied to any of the above areas is also welcome.  Specific topics of interest include: auditory modeling and hearing aids; acoustic beamforming and source localization; classification of acoustic scenes; speaker separation; active noise control and echo cancellation; enhancement; de-reverberation; bioacoustics; music signals analysis, synthesis and modification; music information retrieval;  audio for multimedia and joint audio-video processing; spoken and written language modeling, segmentation, tagging, parsing, understanding, and translation; text mining; speech production, perception, and psychoacoustics; speech analysis, synthesis, and perceptual modeling and coding; robust speech recognition; speaker recognition and characterization; deep learning, online learning, and graphical models applied to speech, audio, and language signals; and implementation aspects ranging from system architecture to fast algorithms.
处理代表音频、语音和语言的信号的理论和方法及其应用。这包括分析、合成、增强、转换、分类和解释这些信号，以及相关信号处理系统的设计、开发和评估。机器学习和模式分析应用于上述任何领域也是受欢迎的。感兴趣的具体主题包括：听觉建模和助听器；声波束形成与声源定位；声场景分类；说话人分离；有源噪声控制和回声消除；增强；去混响；生物声学；音乐信号的分析、合成与修饰；音乐信息检索；多媒体音频和联合音视频处理；口语和书面语建模、切分、标注、句法分析、理解和翻译；文本挖掘；言语产生、感知和心理声学；语音分析、合成、感知建模和编码；鲁棒语音识别；说话人识别与特征描述；应用于语音、音频和语言信号的深度学习、在线学习和图形模型；以及从系统架构到快速算法的实现方面。
--

---
英文摘要：
  Regularization is crucial to the success of many practical deep learning models, in particular in a more often than not scenario where there are only a few to a moderate number of accessible training samples. In addition to weight decay, data augmentation and dropout, regularization based on multi-branch architectures, such as Shake-Shake regularization, has been proven successful in many applications and attracted more and more attention. However, beyond model-based representation augmentation, it is unclear how Shake-Shake regularization helps to provide further improvement on classification tasks, let alone the baffling interaction between batch normalization and shaking. In this work, we present our investigation on Shake-Shake regularization, drawing connections to the vicinal risk minimization principle and discriminative feature learning in verification tasks. Furthermore, we identify a strong resemblance between batch normalized residual blocks and batch normalized recurrent neural networks, where both of them share a similar convergence behavior, which could be mitigated by a proper initialization of batch normalization. Based on the findings, our experiments on speech emotion recognition demonstrate simultaneously an improvement on the classification accuracy and a reduction on the generalization gap both with statistical significance.
---
PDF链接：
https://arxiv.org/pdf/1808.00876