I'm new to draw latex. The below is my code:



% Basis: http://www.texample.net/tikz/examples/neural-network/


\begin{tikzpicture}[shorten >=1pt,->,draw=black!100, node distance=\layersep]
    \tikzstyle{every pin edge}=[<-,shorten <=1pt]
    \tikzstyle{neuron}=[circle,fill=black!25,minimum size=17pt,inner sep=0pt]
    \tikzstyle{input neuron}=[neuron, fill=white!100,draw=black];
    \tikzstyle{output neuron}=[neuron, fill=white!100,draw=black];
    \tikzstyle{hidden neuron}=[neuron, fill=white!100,draw=black];
    \tikzstyle{annot} = [text width=4em, text centered]

% Draw the input layer nodes
\foreach \name / \y in {1,...,3}
% This is the same as writing \foreach \name / \y in {1/1,2/2,3/3,4/4}
    \node[input neuron, pin=left:Word \y] (I-\name) at (0,-\y) {};

% Draw the hidden layer nodes
\foreach \name / \y in {1,...,3}
        node[hidden neuron] (H-\name) at (\layersep,-\y cm) {};

% Draw the output layer node
\node[output neuron,pin={[pin edge={->}]right:Sentiment Result}, right of=H-2] (O1) {};

% Connect every node in the input layer with every node in the
% hidden layer.
\foreach \source in {1,...,3}
    \foreach \dest in {1,...,3}
        \path (I-\source) edge (H-\dest);

% Connect every node in the hidden layer with the output layer
\foreach \source in {1,...,3}
    \path (H-\source) edge (O1);

% Annotate the layers
\node[annot,above of=H-1, node distance=1cm] (hl) {Vector layer};
\node[annot,left of=hl] {Input layer};
\node[annot,right of=hl] {Output layer};

% End of code

result is this: enter image description here

I want to: add 2 notations among Input layer, Vector layer and Output Layer. Also, change the Word 3 to Word n and add dots between Word 2 and Word n.

ThanK you a lot!

  • Have you had a look at the pgf/tikz manual? So far you have copied the example code from http://www.texample.net/tikz/examples/neural-network/ (it's mentioned in the code as a comment) and have modified it slightly. In addition, I changed your title so that is more meaningful. I would start with a less complex code (maybe without a loop) and build the system step-by-step in order to learn the basics. Apr 11, 2017 at 20:13
  • Have a look here tex.stackexchange.com/questions/276817 for example regarding the curly braces (or tex.stackexchange.com/questions/230566). Apr 11, 2017 at 20:16

1 Answer 1


Like this?

enter image description here

\documentclass[tikz, margin=3mm]{standalone}
\usetikzlibrary{chains, decorations.pathreplacing, positioning} 


        node distance = 11mm and 22mm,
          start chain = going below,
every pin edge/.style = {<-, draw=black, shorten <=1pt},
        neuron/.style = {circle, draw, minimum size=17pt,inner sep=0pt,
                         node contents={}},
  input neuron/.style = {neuron, on chain},
         annot/.style = {text width=4em, text centered, node distance = 6mm},
        B/.style args = {#1/#2}{%B: Brace
            decoration={brace, amplitude=5pt,
                        pre=moveto,pre length=1pt,post=moveto,post length=1pt,
                        #2,% for mirroring of brace
% input, hiden and output layer nodes
\foreach \i in {1,2,3}
    \node (ni\i) [input neuron, pin=left:Word \i];
    \node (nh\i) [neuron, right=of ni\i];
% output layer node
\node (out) [neuron,
             pin={[pin edge={->}]right:Sentiment Result},
             right=of nh2];
% Connections between nodes
\foreach \j in {1,2,3}
    \draw[->,shorten >=1pt] (ni\j) -- (nh\j);
    \draw[->,shorten >=1pt] (nh\j) -- (out);
% Annotate the layers 
\node (ai) [annot,above=of ni1.center] {Vector layer};
\node (ah) [annot,above=of nh1.center] {Input layer};
\node (ao) [annot,above=of nh1 -| out] {Output layer};
% braces
\draw[B=1mm/ ]  (ai.north) -- node[above=3mm] {notation 1} (ah.north);
\draw[B=1mm/ ]  (ah.north) -- node[above=3mm] {notation 2} (ao.north);

For brace is intended TikZ library decorations.pathreplacing. Style for them I named B (as Brace). In comparison with your MWE in above obsolete styles definition is replaced with <style name>/.style = {...},, for nodes are used only two styles (neuron and input neuron) which differ only in use of on chain. It is used for simpler placing neuron nodes.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.