updates

684042f3 · xiaotong · 9773724d · 684042f3 · 684042f3 · 684042f3
Commit 684042f3 authored Apr 20, 2020 by xiaotong
--- a/Book/Chapter5/chapter5.tex
+++ b/Book/Chapter5/chapter5.tex
@@ -154,7 +154,7 @@
 %--5.2神经网络基础-----------------------------------------
 \section{神经网络基础}\index{Chapter5.2}
-\parinterval 神经网络是一种由大量的节点（或称神经元）之间相互连接构成的运算模型。那么什么是神经元？神经元之间又是如何连接的？神经网络的数学描述又是什么样的？这一节将围绕这些问题对神经网络的基础知识作进行系统的介绍。
+\parinterval 神经网络是一种由大量的节点（或称神经元）之间相互连接构成的计算模型。那么什么是神经元？神经元之间又是如何连接的？神经网络的数学描述又是什么样的？这一节将围绕这些问题对神经网络的基础知识作进行系统的介绍。
 %--5.2.1线性代数基础---------------------
 \subsection{线性代数基础}\index{Chapter5.2.1} \label{sec:5.2.1}

--- a/Book/mt-book-xelatex.idx
+++ b/Book/mt-book-xelatex.idx
@@ -48,7 +48,7 @@
 \indexentry{Chapter5.4.6.1|hyperpage}{59}
 \indexentry{Chapter5.4.6.2|hyperpage}{61}
 \indexentry{Chapter5.4.6.3|hyperpage}{62}
-\indexentry{Chapter5.5|hyperpage}{63}
+\indexentry{Chapter5.5|hyperpage}{64}
 \indexentry{Chapter5.5.1|hyperpage}{64}
 \indexentry{Chapter5.5.1.1|hyperpage}{65}
 \indexentry{Chapter5.5.1.2|hyperpage}{67}
@@ -60,7 +60,7 @@
 \indexentry{Chapter5.5.3|hyperpage}{72}
 \indexentry{Chapter5.5.3.1|hyperpage}{72}
 \indexentry{Chapter5.5.3.2|hyperpage}{74}
-\indexentry{Chapter5.5.3.3|hyperpage}{75}
+\indexentry{Chapter5.5.3.3|hyperpage}{74}
 \indexentry{Chapter5.5.3.4|hyperpage}{75}
-\indexentry{Chapter5.5.3.5|hyperpage}{76}
+\indexentry{Chapter5.5.3.5|hyperpage}{75}
-\indexentry{Chapter5.6|hyperpage}{77}
+\indexentry{Chapter5.6|hyperpage}{76}
--- a/Book/mt-book-xelatex.ptc
+++ b/Book/mt-book-xelatex.ptc
 \boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax 
+\babel@toc {english}{}
 \defcounter {refsection}{0}\relax 
-\select@language {english}
+\contentsline {part}{\@mypartnumtocformat {I}{神经机器翻译}}{7}{part.1}% 
-\defcounter {refsection}{0}\relax 
-\contentsline {part}{\@mypartnumtocformat {I}{神经机器翻译}}{7}{part.1}
 \ttl@starttoc {default@1}
 \defcounter {refsection}{0}\relax 
-\contentsline {chapter}{\numberline {1}人工神经网络和神经语言建模}{9}{chapter.1}
+\contentsline {chapter}{\numberline {1}人工神经网络和神经语言建模}{9}{chapter.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.1}深度学习与人工神经网络}{10}{section.1.1}
+\contentsline {section}{\numberline {1.1}深度学习与人工神经网络}{10}{section.1.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.1.1}发展简史}{10}{subsection.1.1.1}
+\contentsline {subsection}{\numberline {1.1.1}发展简史}{10}{subsection.1.1.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{早期的人工神经网络和第一次寒冬}{10}{section*.2}
+\contentsline {subsubsection}{早期的人工神经网络和第一次寒冬}{10}{section*.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{神经网络的第二次高潮和第二次寒冬}{11}{section*.3}
+\contentsline {subsubsection}{神经网络的第二次高潮和第二次寒冬}{11}{section*.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{深度学习和神经网络方法的崛起}{12}{section*.4}
+\contentsline {subsubsection}{深度学习和神经网络方法的崛起}{12}{section*.4}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.1.2}为什么需要深度学习}{13}{subsection.1.1.2}
+\contentsline {subsection}{\numberline {1.1.2}为什么需要深度学习}{13}{subsection.1.1.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{端到端学习和表示学习}{13}{section*.6}
+\contentsline {subsubsection}{端到端学习和表示学习}{13}{section*.6}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{深度学习的效果}{14}{section*.8}
+\contentsline {subsubsection}{深度学习的效果}{14}{section*.8}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.2}神经网络基础}{14}{section.1.2}
+\contentsline {section}{\numberline {1.2}神经网络基础}{14}{section.1.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.2.1}线性代数基础}{14}{subsection.1.2.1}
+\contentsline {subsection}{\numberline {1.2.1}线性代数基础}{14}{subsection.1.2.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{标量、向量和矩阵}{15}{section*.10}
+\contentsline {subsubsection}{标量、向量和矩阵}{15}{section*.10}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{矩阵的转置}{16}{section*.11}
+\contentsline {subsubsection}{矩阵的转置}{16}{section*.11}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{矩阵加法和数乘}{16}{section*.12}
+\contentsline {subsubsection}{矩阵加法和数乘}{16}{section*.12}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{矩阵乘法和矩阵点乘}{17}{section*.13}
+\contentsline {subsubsection}{矩阵乘法和矩阵点乘}{17}{section*.13}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{线性映射}{18}{section*.14}
+\contentsline {subsubsection}{线性映射}{18}{section*.14}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{范数}{19}{section*.15}
+\contentsline {subsubsection}{范数}{19}{section*.15}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.2.2}人工神经元和感知机}{20}{subsection.1.2.2}
+\contentsline {subsection}{\numberline {1.2.2}人工神经元和感知机}{20}{subsection.1.2.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）感知机\ \raisebox {0.5mm}{------}\ 最简单的人工神经元模型}{20}{section*.18}
+\contentsline {subsubsection}{（一）感知机\ \raisebox {0.5mm}{------}\ 最简单的人工神经元模型}{20}{section*.18}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）神经元内部权重}{22}{section*.21}
+\contentsline {subsubsection}{（二）神经元内部权重}{22}{section*.21}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）神经元的输入\ \raisebox {0.5mm}{------}\ 离散 vs 连续}{22}{section*.23}
+\contentsline {subsubsection}{（三）神经元的输入\ \raisebox {0.5mm}{------}\ 离散 vs 连续}{22}{section*.23}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（四）神经元内部的参数学习}{23}{section*.25}
+\contentsline {subsubsection}{（四）神经元内部的参数学习}{23}{section*.25}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.2.3}多层神经网络}{24}{subsection.1.2.3}
+\contentsline {subsection}{\numberline {1.2.3}多层神经网络}{24}{subsection.1.2.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{线性变换和激活函数}{24}{section*.27}
+\contentsline {subsubsection}{线性变换和激活函数}{24}{section*.27}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{单层神经网络$\rightarrow $多层神经网络}{26}{section*.34}
+\contentsline {subsubsection}{单层神经网络$\rightarrow $多层神经网络}{26}{section*.34}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.2.4}函数拟合能力}{26}{subsection.1.2.4}
+\contentsline {subsection}{\numberline {1.2.4}函数拟合能力}{26}{subsection.1.2.4}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.3}神经网络的张量实现}{31}{section.1.3}
+\contentsline {section}{\numberline {1.3}神经网络的张量实现}{31}{section.1.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.3.1} 张量及其计算}{32}{subsection.1.3.1}
+\contentsline {subsection}{\numberline {1.3.1} 张量及其计算}{32}{subsection.1.3.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{张量}{32}{section*.44}
+\contentsline {subsubsection}{张量}{32}{section*.44}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{张量的矩阵乘法}{34}{section*.47}
+\contentsline {subsubsection}{张量的矩阵乘法}{34}{section*.47}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{张量的单元操作}{35}{section*.49}
+\contentsline {subsubsection}{张量的单元操作}{35}{section*.49}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.3.2}张量的物理存储形式}{36}{subsection.1.3.2}
+\contentsline {subsection}{\numberline {1.3.2}张量的物理存储形式}{36}{subsection.1.3.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.3.3}使用开源框架实现张量计算}{36}{subsection.1.3.3}
+\contentsline {subsection}{\numberline {1.3.3}使用开源框架实现张量计算}{36}{subsection.1.3.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.3.4}神经网络中的前向传播}{40}{subsection.1.3.4}
+\contentsline {subsection}{\numberline {1.3.4}神经网络中的前向传播}{40}{subsection.1.3.4}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.3.5}神经网络实例}{41}{subsection.1.3.5}
+\contentsline {subsection}{\numberline {1.3.5}神经网络实例}{41}{subsection.1.3.5}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.4}神经网络的参数训练}{42}{section.1.4}
+\contentsline {section}{\numberline {1.4}神经网络的参数训练}{42}{section.1.4}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.1}损失函数}{43}{subsection.1.4.1}
+\contentsline {subsection}{\numberline {1.4.1}损失函数}{43}{subsection.1.4.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.2}基于梯度的参数优化}{44}{subsection.1.4.2}
+\contentsline {subsection}{\numberline {1.4.2}基于梯度的参数优化}{44}{subsection.1.4.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）梯度下降}{45}{section*.67}
+\contentsline {subsubsection}{（一）梯度下降}{45}{section*.67}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）梯度获取}{47}{section*.69}
+\contentsline {subsubsection}{（二）梯度获取}{47}{section*.69}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）基于梯度的方法的变种和改进}{49}{section*.73}
+\contentsline {subsubsection}{（三）基于梯度的方法的变种和改进}{49}{section*.73}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.3}参数更新的并行化策略}{52}{subsection.1.4.3}
+\contentsline {subsection}{\numberline {1.4.3}参数更新的并行化策略}{52}{subsection.1.4.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.4}梯度消失、梯度爆炸和稳定性训练}{54}{subsection.1.4.4}
+\contentsline {subsection}{\numberline {1.4.4}梯度消失、梯度爆炸和稳定性训练}{54}{subsection.1.4.4}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）梯度消失现象及解决方法}{54}{section*.76}
+\contentsline {subsubsection}{（一）梯度消失现象及解决方法}{54}{section*.76}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）梯度爆炸现象及解决方法}{55}{section*.80}
+\contentsline {subsubsection}{（二）梯度爆炸现象及解决方法}{55}{section*.80}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）稳定性训练}{56}{section*.81}
+\contentsline {subsubsection}{（三）稳定性训练}{56}{section*.81}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.5}过拟合}{57}{subsection.1.4.5}
+\contentsline {subsection}{\numberline {1.4.5}过拟合}{57}{subsection.1.4.5}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.4.6}反向传播}{58}{subsection.1.4.6}
+\contentsline {subsection}{\numberline {1.4.6}反向传播}{58}{subsection.1.4.6}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）输出层的反向传播}{59}{section*.84}
+\contentsline {subsubsection}{（一）输出层的反向传播}{59}{section*.84}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）隐藏层的反向传播}{61}{section*.88}
+\contentsline {subsubsection}{（二）隐藏层的反向传播}{61}{section*.88}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）程序实现}{62}{section*.91}
+\contentsline {subsubsection}{（三）程序实现}{62}{section*.91}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.5}神经语言模型}{63}{section.1.5}
+\contentsline {section}{\numberline {1.5}神经语言模型}{64}{section.1.5}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.5.1}基于神经网络的语言建模}{64}{subsection.1.5.1}
+\contentsline {subsection}{\numberline {1.5.1}基于神经网络的语言建模}{64}{subsection.1.5.1}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）基于前馈神经网络的语言模型}{65}{section*.94}
+\contentsline {subsubsection}{（一）基于前馈神经网络的语言模型}{65}{section*.94}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）基于循环神经网络的语言模型}{67}{section*.97}
+\contentsline {subsubsection}{（二）基于循环神经网络的语言模型}{67}{section*.97}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）基于自注意力机制的语言模型}{68}{section*.99}
+\contentsline {subsubsection}{（三）基于自注意力机制的语言模型}{68}{section*.99}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（四）语言模型的评价}{69}{section*.101}
+\contentsline {subsubsection}{（四）语言模型的评价}{69}{section*.101}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.5.2}单词表示模型}{70}{subsection.1.5.2}
+\contentsline {subsection}{\numberline {1.5.2}单词表示模型}{70}{subsection.1.5.2}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）One-hot编码}{70}{section*.102}
+\contentsline {subsubsection}{（一）One-hot编码}{70}{section*.102}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）分布式表示}{70}{section*.104}
+\contentsline {subsubsection}{（二）分布式表示}{70}{section*.104}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsection}{\numberline {1.5.3}句子表示模型及预训练}{72}{subsection.1.5.3}
+\contentsline {subsection}{\numberline {1.5.3}句子表示模型及预训练}{72}{subsection.1.5.3}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（一）简单的上下文表示模型}{72}{section*.108}
+\contentsline {subsubsection}{（一）简单的上下文表示模型}{72}{section*.108}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（二）ELMO模型}{74}{section*.111}
+\contentsline {subsubsection}{（二）ELMO模型}{74}{section*.111}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（三）GPT模型}{75}{section*.113}
+\contentsline {subsubsection}{（三）GPT模型}{74}{section*.113}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（四）BERT模型}{75}{section*.115}
+\contentsline {subsubsection}{（四）BERT模型}{75}{section*.115}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {subsubsection}{（五）为什么要预训练？}{76}{section*.117}
+\contentsline {subsubsection}{（五）为什么要预训练？}{75}{section*.117}% 
 \defcounter {refsection}{0}\relax 
-\contentsline {section}{\numberline {1.6}小结及深入阅读}{77}{section.1.6}
+\contentsline {section}{\numberline {1.6}小结及深入阅读}{76}{section.1.6}% 
 \contentsfinish 
--- a/Book/mt-book-xelatex.tex
+++ b/Book/mt-book-xelatex.tex
@@ -112,13 +112,13 @@
 %	CHAPTERS
 %----------------------------------------------------------------------------------------
-\include{Chapter1/chapter1}
+%\include{Chapter1/chapter1}
-\include{Chapter2/chapter2}
+%\include{Chapter2/chapter2}
-\include{Chapter3/chapter3}
+%\include{Chapter3/chapter3}
-\include{Chapter4/chapter4}
+%\include{Chapter4/chapter4}
 \include{Chapter5/chapter5}
-\include{Chapter6/chapter6}
+%\include{Chapter6/chapter6}
-\include{ChapterAppend/chapterappend}
+%\include{ChapterAppend/chapterappend}