An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling
2018-05-16 16:09:15
Introduction:
本文提出一种 TCN (Temporal Convolutional Networks) 网络结构,用卷积的方式进行序列数据的处理,并且取得了和更加复杂的 RNN、LSTM、GRU 等模型相当的精度。
Temporal Convolutional Networks :
TCNs 的特点有:
1). the convolutions in the architecture are casual, meaning that there is no information "leakage" from future to past;
2). the architecture can take a sequence of any length and map it to an output sequence of the same length, just as with an RNN.
3). we emphasize how to build very long effective history size using a combination of very deep networks and dilated convolutions.
1. Sequence Modeling :
输入是一个序列,如:x0, ... , xT;对应输出的 label 是 y0, ... , yT。而序列模型就是要学习这么一个映射函数,从输入到输出,即:

但是,这种方法以 autoregressive prediction 为核心,但是,不能直接捕获下面的 domain:machine translation, or sequence to sequence prediction,因为:在这些情况下,整个的输入可以被用来预测每一个输出(since in these cases the entire input sentence can be used to predict each output)。
2. Casual Convlutions :
TCNs 是基于两个原则的:
(1)the fact that the network produces an output of the same length as the input(输入和输出保持一致),
(2)the fact that there can be no leakage from the future into the past(从未来到过去,没做信息泄露).
为了满足第一点,TCNs 采用全卷积网络结构。每一个 hidden layer 和 input layer 是相同的,and zero padding of length (kernel size -1) is added to keep subsequent layers the same length as previous ones.
为了满足第二点,TCNs 采用 casual convolutions, where an output at time t is convolved only with elements from time t and earlier in the previous layer.
那么,TCNs 就是:TCN = 1D FCN + casual convolutions.
这种基本的设计方法的主要不足之处在于:为了得到一个较长的历史尺寸,我们需要一个非常深的网络 或者 非常大的 filters。
3. Dilated Convolutions :
为了使得 filter size 尽可能大,我们采用 dilated convolutions,that enable an exponentially large receptive field.
正式的,对于 1-D sequence input x , 以及 a filter f , 空洞卷积操作 F 在输入序列中元素 s 可以定义为:

其中,d 是空洞系数,k 是filter size,s-di accounts for the direction of the past.
Using larger dilation enables an output at the top level to represent a wider range of inputs, thus effectively expanding the receptive field of a ConvNet.
这给我们增加 TCN 的感受野,提供了两个思路:
(1). choosing larger filter sizes k ;
(2). increasing the dilation factor d, where the effective history of one such layer is (k-1)d.
4. Residual Connnections :
此处的残差连接,就是借鉴了何凯明的 residual network,即:将之前的信息和转换后的信息,都作为当前的输入,从而使得网络层数非常深的时候,仍然能够得到不错的效果:

This effectively allows layers to learn modifications to the identity mapping rather than the entire transformation, which has repeatly been shown to benefit very deep networks.

5. Discussion :
本小结总结了 TCN 用于 sequence modeling 的几个优势和劣势:
(1)Parallelilsm RNN 的预测总是需要上一个时刻完毕后,才可以进行。但是 CNN 的则没有这个约束,因为 the same filter is used in each layer.
(2)Flexible receptive field size TCN 可以在不同的 layer 采用不同的 receptive field size。
(3)Stable gradients 不同于 RNN 结构,TCN has a backpropagation path different from the temporal direction of the sequence. 所以 TCN 就没有 RNN 结构中梯度消失或者梯度爆炸的情况。
(4)Low memory requirement for training LSTM or GRU 由于需要存储很多 cell gates 的信息,所以需要很大的内存,但是由于 filter 是共享的,内存的利用仅仅依赖于网络的深度。而作者也发现:gated RNNs likely to use up to a multiplicative factor more memory than TCNs.
(5)Variable length inputs TCNs can also take in inputs of arbitrary length by sliding the 1D convolutional kernels.
两个明显的劣势在于:
(1)Data storage during evalution.
(2)Potential parameter change for a transfer of domain.
--- Reference
Code: http://github.com/locuslab/TCN.
An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling的更多相关文章
- 新手教程之:循环网络和LSTM指南 (A Beginner’s Guide to Recurrent Networks and LSTMs)
新手教程之:循环网络和LSTM指南 (A Beginner’s Guide to Recurrent Networks and LSTMs) 本文翻译自:http://deeplearning4j.o ...
- 论文笔记之:Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grained Recognition
Fully Convolutional Attention Localization Networks: Efficient Attention Localization for Fine-Grain ...
- 论文笔记之:UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS
UNSUPERVISED REPRESENTATION LEARNING WITH DEEP CONVOLUTIONAL GENERATIVE ADVERSARIAL NETWORKS ICLR 2 ...
- Recurrent Neural Network Language Modeling Toolkit代码学习
Recurrent Neural Network Language Modeling Toolkit 工具使用点击打开链接 本博客地址:http://blog.csdn.net/wangxingin ...
- Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models
Empirical Analysis of Beam Search Performance Degradation in Neural Sequence Models 2019-06-13 10:2 ...
- Empirical Evaluation of Speaker Adaptation on DNN based Acoustic Model
DNN声学模型说话人自适应的经验性评估 年3月27日 发表于:Sound (cs.SD); Computation and Language (cs.CL); Audio and Speech Pro ...
- Combining STDP and Reward-Modulated STDP in Deep Convolutional Spiking Neural Networks for Digit Recognition
郑重声明:原文参见标题,如有侵权,请联系作者,将会撤销发布! Abstract 灵长类视觉系统激发了深度人工神经网络的发展,使计算机视觉领域发生了革命性的变化.然而,这些网络的能量效率比它们的生物学对 ...
- RNN(2) ------ “《A Critical Review of Recurrent Neural Networks for Sequence Learning》RNN综述性论文讲解”(转载)
原文链接:http://blog.csdn.net/xizero00/article/details/51225065 一.论文所解决的问题 现有的关于RNN这一类网络的综述太少了,并且论文之间的符号 ...
- Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks(paper)
本文重点: 和一般形式的文本处理方式一样,并没有特别大的差异,文章的重点在于提出了一个相似度矩阵 计算过程介绍: query和document中的首先通过word embedding处理后获得对应的表 ...
随机推荐
- html5-增强的表单
<!DOCTYPE html><html lang="en"><head> <meta charset="UTF-8&qu ...
- Shell Necklace (dp递推改cdq分治 + fft)
首先读出题意,然后发现这是一道DP,我们可以获得递推式为 然后就知道,不行啊,时间复杂度为O(n2),然后又可以根据递推式看出这里面可以拆解成多项式乘法,但是即使用了fft,我们还需要做n次多项式乘法 ...
- Java将对象保存到文件中/从文件中读取对象
1.保存对象到文件中 Java语言只能将实现了Serializable接口的类的对象保存到文件中,利用如下方法即可: public static void writeObjectToFile(Obje ...
- LoadLibrary加载动态库失败
[1]LoadLibrary加载动态库失败的可能原因以及解决方案: (1)dll动态库文件路径不对.此场景细分为以下几种情况: 1.1 文件路径的确错误.比如:本来欲加载的是A文件夹下的动态库a.dl ...
- python内置函数bin
bin() 返回一个整数 int 或者长整数 long int 的二进制表示. 代码示例: print(bin(10)) 运行结果: F:\dev\python\python.exe F:/pyCha ...
- sql之left join、right join、inner join的区别,连接自己时的查询结果测试
sql之left join.right join.inner join的区别 left join(左联接) 返回包括左表中的所有记录和右表中联结字段相等的记录 right join(右联接) 返回包括 ...
- DB2的空间数据库管理复杂配置
计算机条件: a机器:linux系统 安装arcgis server b机器:windows系统 安装catalog c机器:linux系统 安装DB2 ...
- How to use Nissan consult 3 plus to check, make key and program?
How to use Nissan consult 3 plus to test Nissan? Firstly: get one particular Nissan consult 3 plus. ...
- ORCAl存储过程
1.存储过程结构 1.1 第一个存储过程 create or replace procedure proc1( para1 varchar2, para2 out varchar2, para3 in ...
- 自学java第六周的总结
在这个星期里,我主要将以前看过的复习了一遍,并且阅读并做了相关的题. 下个星期继续努力.