我创建了下图：
\documentclass{article}
\usepackage{tikz}
\usepackage{float}
\usetikzlibrary{positioning, quotes, arrows.meta}
\begin{document}
\tikzset{%
every neuron/.style={
circle,
draw,
minimum size=1cm
},
neuron missing/.style={
draw=none,
scale=3.5,
text height=0.333cm,
execute at begin node=\color{black}$\vdots$,
fill=none
},
}
\begin{figure}[H]
\centering
\begin{tikzpicture}[x=1.5cm, y=1.5cm, >=stealth, scale=0.9, every node/.style={transform shape}]
\pgfmathsetmacro{\cubex}{2.5}
\pgfmathsetmacro{\cubey}{1}
\pgfmathsetmacro{\cubez}{1.5}
\draw [draw=black, every edge/.append style={draw=black, densely dashed, opacity=.5}]
(-2,0.5,0) coordinate (o) -- ++(-\cubex,0,0) coordinate (a) -- ++(0,-\cubey,0) coordinate (b) edge coordinate [pos=1] (g) ++(0,0,-\cubez) -- ++(\cubex,0,0) coordinate (c) -- cycle
(o) -- ++(0,0,-\cubez) coordinate (d) -- ++(0,-\cubey,0) coordinate (e) edge (g) -- (c) -- cycle
(o) -- (a) -- ++(0,0,-\cubez) coordinate (f) edge (g) -- (d) -- cycle node[pos=2] {data};
\path [every edge/.append style={draw=black, |-|}]
(b) +(0,-5pt) coordinate (b1) edge ["t"'] (b1 -| c)
(b) +(-5pt,0) coordinate (b2) edge ["i"] (b2 |- a)
(c) +(3.5pt,-3.5pt) coordinate (c2) edge ["k"'] ([xshift=3.5pt,yshift=-3.5pt]e)
;
\foreach \m/\l [count=\y] in {1,2,missing,3}
\node [every neuron/.try, neuron \m/.try] (input-\m) at (0,2.5-\y) {};
\foreach \m [count=\y] in {1,missing,2}
\node [fill=black!50, every neuron/.try, neuron \m/.try ] (hidden-\m) at (2,2.2-\y*1.1) {};
\foreach \m [count=\y] in {1}
\node [every neuron/.try, neuron \m/.try, fill=black] (output-\m) at (4,1-\y) {};
\foreach \m [count=\y] in {1}
\node [every neuron/.try, neuron \m/.try, fill=black] (nt-\m) at (4,0-\y) {};
\foreach \m [count=\y] in {1}
\node [every neuron/.try, neuron \m/.try, fill=black] (ew-\m) at (4,2-\y) {};
\foreach \l [count=\i] in {1,2,n}
\draw [<-] (input-\i) -- ++(-1,0)
node [above, midway] {$I_\l$};
\foreach \l [count=\i] in {1,m}
\node [above] at (hidden-\i.north) {$H_\l$};
\node [above] at (ew-1.north) {$ew$};
\node [below] at (nt-1.south) {$nt$};
\foreach \l [count=\i] in {1}
\draw [->] (output-\i) -- ++(1,0)
node [above, midway] {$O_\l$};
\foreach \i in {1,...,3}
\foreach \j in {1,...,2}
\draw [->] (input-\i) -- (hidden-\j);
\foreach \i in {1,...,2}
\foreach \j in {1}
\draw [->] (hidden-\i) -- (output-\j);
\draw [->] (nt-1) -- (output-1);
\draw [->] (ew-1) -- (output-1);
\foreach \l [count=\x from 0] in {Input, Hidden, Ouput}
\node [align=center, above] at (\x*2,2) {\l \\[-0.4em] layer};
\pgfmathsetmacro{\rectx}{8}
\pgfmathsetmacro{\recty}{0.5}
\draw[draw=black] (5.5,-0.5) rectangle (\rectx,\recty) node[pos=.5] {weights};
\draw[black, |-|, yshift=-5pt] (5.5,-0.5) --node[below]{t} (\rectx,-0.5);
\draw[black, |-|, xshift=-5pt] (5.5,-0.5) --node[left]{i} (5.5,\recty);
\end{tikzpicture}
\caption{Neural Network Structure}
\end{figure}
\end{document}
由此得到以下图片：
但是，我想让左边的箭头看起来如下；即，它们应该从左侧框的中间（垂直）到达输入层，如图所示：
答案1
添加一个额外的点来连接这三条线。我将其添加到(-1.5,0)：
\foreach \l [count=\i] in {1,2,n}
\draw [<-] (input-\i) -- ++(-1,0)node [above, midway] {$I_\l$} -- (-1.5,0);
