update

Section05-Neural-Networks-and-Language-Modeling/section05.tex

@@ -311,7 +311,7 @@ y = f(w \cdot x + b)
 \begin{center}
 \begin{tikzpicture}
 \begin{scope}
-\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow] (neuron) at (0,0) {};
+\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow={shadow xshift=0.1em,shadow yshift=-0.1em}] (neuron) at (0,0) {};
 \node [anchor=east] (x1) at ([xshift=-6em]neuron.west) {\Large{$x_1$}};
 \node [anchor=center] (x0) at ([yshift=3em]x1.center) {\Large{$x_0$}};
 \node [anchor=center] (x2) at ([yshift=-3em]x1.center) {\Large{$x_2$}};
@@ -388,7 +388,7 @@ y = f(w \cdot x + b)
 \begin{center}
 \begin{tikzpicture}
 \begin{scope}
-\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow] (neuron) at (0,0) {};
+\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow={shadow xshift=0.1em,shadow yshift=-0.1em}] (neuron) at (0,0) {};
 \node [anchor=east] (x1) at ([xshift=-6em]neuron.west) {$x_1$:票价够低？};
 \node [anchor=center] (x0) at ([yshift=3em]x1.center) {$x_0$:距离够近？};
 \node [anchor=center] (x2) at ([yshift=-3em]x1.center) {$x_2$:女友喜欢？};
@@ -490,7 +490,7 @@ y = f(w \cdot x + b)
 \begin{center}
 \begin{tikzpicture}
 \begin{scope}
-\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow] (neuron) at (0,0) {};
+\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow={shadow xshift=0.1em,shadow yshift=-0.1em}] (neuron) at (0,0) {};
 \node [anchor=east] (x1) at ([xshift=-6em]neuron.west) {$x_1$:便宜程度\ \ \ \ };
 \node [anchor=center] (x0) at ([yshift=3em]x1.center) {$x_0$:远近程度\ \ \ \ };
 \node [anchor=center] (x2) at ([yshift=-3em]x1.center) {$x_2$:女友喜欢？};
@@ -530,7 +530,7 @@ y = f(w \cdot x + b)
 \item<2-> \textbf{当然}，你是一个勇于实践的人
     \begin{itemize}
     \item 方法很简单：不断地尝试，根据结构不断地调整权重
-    \item<10-> 在进行了很多次实验后，发现了相对好的一组决策模型
+    \item<10-> 在进行了很多次实验后，发现了相对好的一组权重
     \end{itemize}
 \end{itemize}
 
@@ -628,6 +628,74 @@ y = f(w \cdot x + b)
 %%%------------------------------------------------------------------------------------------------------------
 %%% 感知机 - 一个例子 - 总结
 \begin{frame}{一个例子 - 总结}
+\begin{itemize}
+\item 即便对于一个简单问题，如何设计一种合理方法的准确的进行决策并不简单。在上面这个模型中，还有一些\alert{问题}需要回答
+    \begin{itemize}
+    \item<2-> 对问题建模，即：定义输入$\{x_i\}$的形式
+    \item<3-> 设计有效的决策模型，即：定义$y$
+    \item<4-> 决定模型所涉及的参数（如权重$\{w_i\}$）的最优值
+    \end{itemize}
+\end{itemize}
+
+\vspace{-2em}
+\begin{center}
+\begin{tikzpicture}
+\begin{scope}
+\node [anchor=center,circle,draw,ublue,very thick,minimum size=3.5em,fill=white,drop shadow={shadow xshift=0.1em,shadow yshift=-0.1em}] (neuron) at (0,0) {};
+
+\visible<2->{
+\node [anchor=east] (x1) at ([xshift=-6em]neuron.west) {$x_1$:便宜程度\ \ \ \ };
+\node [anchor=center] (x0) at ([yshift=3em]x1.center) {$x_0$:远近程度\ \ \ \ };
+\node [anchor=center] (x2) at ([yshift=-3em]x1.center) {$x_2$:女友喜欢？};
+}
+
+\visible<3->{
+\node [anchor=west] (y) at ([xshift=2em]neuron.east) {$y$:去？还是不去？};
+\node [anchor=center] (neuronmath) at (neuron.center) {\small{$\sum \ge \sigma$}};
+}
+
+\draw [->,thick] (neuron.east) -- (y.west);
+
+\draw [->,thick] (x0.east) -- (neuron.150);
+\draw [->,thick] (x1.east) -- (neuron.180);
+\draw [->,thick] (x2.east) -- (neuron.210);
+
+\visible<4->{
+\draw [->,thick] (x0.east) -- (neuron.150) node [pos=0.5,above,yshift=0.2em] {$w_0$};
+\draw [->,thick] (x1.east) -- (neuron.180) node [pos=0.5,above,yshift=-0.1em] {$w_1$};
+\draw [->,thick] (x2.east) -- (neuron.210) node [pos=0.5,above,yshift=0.1em] {$w_2$};
+}
+
+\end{scope}
+\end{tikzpicture}
+\end{center}
+
+\vspace{-0.5em}
+
+\begin{itemize}
+\item<5-> \textbf{当然}，后面的内容会涉及上面的问题，而且不止这些 :)
+\end{itemize}
+
+\end{frame}
+
+%%%------------------------------------------------------------------------------------------------------------
+%%% outline
+\begin{frame}{入门神经网络(深度学习)的三个基本问题}
+
+\begin{center}
+\begin{tikzpicture}
+
+{\Large
+\node [anchor=west,draw,ublue,very thick,rounded corners=4pt,text width=18em,align=left,fill=white,drop shadow={shadow xshift=0.2em,shadow yshift=-0.2em}] (p1) at (0,0) {\black{\textbf{1. 人工神经网络的数学描述是什么？}}\\\black{\textbf{\hspace{0.9em} 如何实现这种数学模型？}}};
+
+\node [anchor=north west,draw,ublue,very thick,rounded corners=4pt,text width=18em,align=left,fill=white,drop shadow={shadow xshift=0.2em,shadow yshift=-0.2em}] (p21) at ([yshift=-1em]p1.south west) {\black{\textbf{2. 如何将简单的网络单元组合成更}}\\\black{\textbf{\hspace{0.9em} 强大的模型？}}};
+
+\node [anchor=north west,draw,ublue,very thick,rounded corners=4pt,text width=18em,align=left,fill=white,drop shadow={shadow xshift=0.2em,shadow yshift=-0.2em}] (p22) at ([yshift=-1em]p21.south west) {\black{\textbf{3. 如何对模型中的参数进行学习？}}\\\black{\textbf{\hspace{0.9em} 如何使用学习到的模型进行推断？}}};
+}
+
+\end{tikzpicture}
+\end{center}
+
 \end{frame}
 
 %%%------------------------------------------------------------------------------------------------------------