Skip to content

T
Toy-MT-Introduction
Commit 684042f3 by xiaotong
Options

updates

parent 9773724d
正在显示 包含 80 行增加 和 81 行删除
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}
......
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{Chapter5.6|hyperpage}{77}
\indexentry{Chapter5.5.3.5|hyperpage}{75}
\indexentry{Chapter5.6|hyperpage}{76}
Book/mt-book-xelatex.ptc
\boolfalse {citerequest}\boolfalse {citetracker}\boolfalse {pagetracker}\boolfalse {backtracker}\relax
\babel@toc {english}{}
\defcounter {refsection}{0}\relax
\select@language {english}
\defcounter {refsection}{0}\relax
\contentsline {part}{\@mypartnumtocformat {I}{神经机器翻译}}{7}{part.1}
\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
Book/mt-book-xelatex.tex
......@@ -112,13 +112,13 @@
% CHAPTERS
%----------------------------------------------------------------------------------------
\include{Chapter1/chapter1}
\include{Chapter2/chapter2}
\include{Chapter3/chapter3}
\include{Chapter4/chapter4}
%\include{Chapter1/chapter1}
%\include{Chapter2/chapter2}
%\include{Chapter3/chapter3}
%\include{Chapter4/chapter4}
\include{Chapter5/chapter5}
\include{Chapter6/chapter6}
\include{ChapterAppend/chapterappend}
%\include{Chapter6/chapter6}
%\include{ChapterAppend/chapterappend}
......
Markdown 格式
0% 或
您添加了 0 人 到此讨论。请谨慎行事。
请先完成此评论的编辑！
请 注册 或者 后发表评论