合并分支 'zengxin' 到 'caorunzhe'

Zengxin

查看合并请求 !403

Chapter11/Figures/figure-structural-comparison-b.tex

@@ -2,7 +2,7 @@
 
 
 \begin{tikzpicture}[node distance = 0cm]
-\node(num1_0)[num, fill = blue!40]{\textbf{\textcolor{white}0}};
+\node(num1_0)[num, fill = blue!40]{\textcolor{white}{$\mathbi{0}$}};
 \node(num1_1)[num,right of = num1_0,xshift = 1.2cm]{$\mathbi{e}_1$};
 \node(num1_2)[num,right of = num1_1,xshift = 1.2cm]{\textcolor{blue!70}{$\mathbi{e}_2$}};
 \node(num1_3)[num,right of = num1_2,xshift = 1.2cm]{\textcolor{blue!70}{$\mathbi{e}_3$}};
@@ -12,11 +12,11 @@
 \node(num1_7)[num,right of = num1_6,xshift = 1.2cm]{\textcolor{blue!70}{$\mathbi{e}_7$}};
 \node(num1_8)[num,right of = num1_7,xshift = 1.2cm]{\textcolor{blue!70}{$\mathbi{e}_8$}};
 \node(num1_9)[num,right of = num1_8,xshift = 1.2cm]{$\mathbi{e}_9$};
-\node(num1_10)[num,right of = num1_9,xshift = 1.2cm, fill = blue!40]{\textbf0};
+\node(num1_10)[num,right of = num1_9,xshift = 1.2cm, fill = blue!40]{$\mathbi{0}$};
 \node(A)[below of = num2,yshift = -0.6cm]{A};
 \node(B)[below of = num8,yshift = -0.6cm]{B};
 
-\node(num2_0)[num,above of = num1_0,yshift = 1.2cm, fill = blue!40]{\textbf{\textcolor{white}0}};
+\node(num2_0)[num,above of = num1_0,yshift = 1.2cm, fill = blue!40]{\textcolor{white}{$\mathbi{0}$}};
 \node(num2_1)[num,right of = num2_0,xshift = 1.2cm]{\textbf2};
 \node(num2_2)[num,right of = num2_1,xshift = 1.2cm]{\textbf2};
 \node(num2_3)[num,right of = num2_2,xshift = 1.2cm]{\textbf{\textcolor{blue!70}2}};
@@ -26,9 +26,9 @@
 \node(num2_7)[num,right of = num2_6,xshift = 1.2cm]{\textbf{\textcolor{blue!70}2}};
 \node(num2_8)[num,right of = num2_7,xshift = 1.2cm]{\textbf2};
 \node(num2_9)[num,right of = num2_8,xshift = 1.2cm]{\textbf2};
-\node(num2_10)[num,right of = num2_9,xshift = 1.2cm, fill = blue!40]{\textbf0};
+\node(num2_10)[num,right of = num2_9,xshift = 1.2cm, fill = blue!40]{$\mathbi{0}$};
 
-\node(num3_0)[num,above of = num2_0,yshift = 1.2cm, fill = blue!40]{\textbf{\textcolor{white}0}};
+\node(num3_0)[num,above of = num2_0,yshift = 1.2cm, fill = blue!40]{\textcolor{white}{$\mathbi{0}$}};
 \node(num3_1)[num,right of = num3_0,xshift = 1.2cm]{\textbf3};
 \node(num3_2)[num,right of = num3_1,xshift = 1.2cm]{\textbf3};
 \node(num3_3)[num,right of = num3_2,xshift = 1.2cm]{\textbf3};
@@ -38,9 +38,9 @@
 \node(num3_7)[num,right of = num3_6,xshift = 1.2cm]{\textbf3};
 \node(num3_8)[num,right of = num3_7,xshift = 1.2cm]{\textbf3};
 \node(num3_9)[num,right of = num3_8,xshift = 1.2cm]{\textbf3};
-\node(num3_10)[num,right of = num3_9,xshift = 1.2cm, fill = blue!40]{\textbf0};
+\node(num3_10)[num,right of = num3_9,xshift = 1.2cm, fill = blue!40]{$\mathbi{0}$};
 
-\node(num4_0)[num,above of = num3_0,yshift = 1.2cm, fill = blue!40]{\textbf{\textcolor{white}0}};
+\node(num4_0)[num,above of = num3_0,yshift = 1.2cm, fill = blue!40]{\textcolor{white}{$\mathbi{0}$}};
 \node(num4_1)[num,right of = num4_0,xshift = 1.2cm]{\textbf4};
 \node(num4_2)[num,right of = num4_1,xshift = 1.2cm]{\textbf4};
 \node(num4_3)[num,right of = num4_2,xshift = 1.2cm]{\textbf4};
@@ -50,7 +50,7 @@
 \node(num4_7)[num,right of = num4_6,xshift = 1.2cm]{\textbf4};
 \node(num4_8)[num,right of = num4_7,xshift = 1.2cm]{\textbf4};
 \node(num4_9)[num,right of = num4_8,xshift = 1.2cm]{\textbf4};
-\node(num4_10)[num,right of = num4_9,xshift = 1.2cm, fill = blue!40]{\textbf0};
+\node(num4_10)[num,right of = num4_9,xshift = 1.2cm, fill = blue!40]{$\mathbi{0}$};
 
 \draw [->, thick](num1_0.north)--([xshift=-0.1em,yshift=-0.1em]num2_1.south);
 \draw [->, thick](num2_0.north)--([xshift=-0.1em,yshift=-0.1em]num3_1.south);

Chapter11/chapter11.tex

@@ -176,7 +176,7 @@
 %\input{./Chapter11/Figures/figure-f }
 \subfigure[循环神经网络的串行结构（$O(n)$）]{\input{./Chapter11/Figures/figure-structural-comparison-a}}
 \subfigure[卷积神经网络的层级结构（$O(n/k)$）]{\input{./Chapter11/Figures/figure-structural-comparison-b}}
-\caption{串行及层级结构对比（$\mathbi{e}_i$表示词嵌入，0表示0向量，2,3,4表示第几层）}
+\caption{串行及层级结构对比（$\mathbi{e}_i$表示词嵌入，$\mathbi{0}$表示$\mathbi{0}$向量，2,3,4表示第几层）}
 \label{fig:11-9}
 \end{figure}
 %----------------------------------------------
@@ -440,7 +440,7 @@
 
 \section{局部模型的改进}
 
-\parinterval 在序列建模中，卷积神经网络可以通过参数共享，高效地捕捉局部上下文特征，如图\ref{fig:11-11}所示。但是通过进一步分析可以发现，在标准卷积操作中包括了不同词和不同通道之间两种信息的交互，每个卷积核都是对相邻词的不同通道进行卷积，参数量为$K \times O$。其中$K$为卷积核大小，$O$为输入的通道数，即单词表示的维度大小。因此$N$个卷积核总共的参数量为$K \times O \times N$。这里涉及卷积核大小、输入通道数和输出通道数三个维度，因此计算复杂度较高。为了进一步提升计算效率，降低参数量，一些研究人员提出{\small\bfnew{深度可分离卷积}}\index{深度可分离卷积}（Depthwise Separable Convolution）\index{Depthwise Separable Convolution}，将空间维度和通道间的信息交互分离成深度卷积（也叫逐通道卷积，Depthwise Convolution）\index{逐通道卷积，Depthwise Convolution}和{\small\bfnew{逐点卷积}} \index{逐点卷积}（Pointwise Convolution）\index{Pointwise Convolution} 两部分\upcite{Chollet2017XceptionDL,Howard2017MobileNetsEC}。除了直接将深度可分离卷积应用到神经机器翻译中\upcite{Kaiser2018DepthwiseSC}，研究人员提出使用更高效的{\small\bfnew{轻量卷积}}\index{轻量卷积}（Lightweight Convolution）\index{Lightweight Convolution}和{\small\bfnew{动态卷积}}\index{动态卷积}（Dynamic convolution）\index{Dynamic convolution}来进行不同词之间的特征提取\upcite{Wu2019PayLA}。本节将主要介绍这些改进的卷积操作。在后续章节中也会看到这些模型在神经机器翻译中的应用。
+\parinterval 在序列建模中，卷积神经网络可以通过参数共享，高效地捕捉局部上下文特征，如图\ref{fig:11-11}所示。但是通过进一步分析可以发现，在标准卷积操作中包括了不同词和不同通道之间两种信息的交互，每个卷积核都是对相邻词的不同通道进行卷积，参数量为$K \times O$。其中$K$为卷积核大小，$O$为输入的通道数，即单词表示的维度大小。因此$N$个卷积核总共的参数量为$K \times O \times N$。这里涉及卷积核大小、输入通道数和输出通道数三个维度，因此计算复杂度较高。为了进一步提升计算效率，降低参数量，一些研究人员提出{\small\bfnew{深度可分离卷积}}\index{深度可分离卷积}（Depthwise Separable Convolution）\index{Depthwise Separable Convolution}，将空间维度和通道间的信息交互分离成深度卷积（也叫逐通道卷积，Depthwise Convolution）\index{逐通道卷积，Depthwise Convolution}和{\small\bfnew{逐点卷积}} \index{逐点卷积}（Pointwise Convolution）\index{Pointwise Convolution} 两部分\upcite{Chollet2017XceptionDL,Howard2017MobileNetsEC}。除了直接将深度可分离卷积应用到神经机器翻译中\upcite{Kaiser2018DepthwiseSC}，研究人员提出使用更高效的{\small\bfnew{轻量卷积}}\index{轻量卷积}（Lightweight Convolution）\index{Lightweight Convolution}和{\small\bfnew{动态卷积}}\index{动态卷积}（Dynamic Convolution）\index{Dynamic convolution}来进行不同词之间的特征提取\upcite{Wu2019PayLA}。本节将主要介绍这些改进的卷积操作。在后续章节中也会看到这些模型在神经机器翻译中的应用。
 
 %----------------------------------------------------------------------------------------
 %    NEW SUB-SECTION