With the output

$\%$ Generate XOR function using McCulloch$-$Pitts neuron by writing an M$-$file.

$\%$XOR function using McCulloch$-$Pitts neuron

clear all

close all;

clc;

$\%$Getting weights and threshold value

disp$(\text{'}$Enter weights'$)$;

w$1=$input$(\text{'}$Weight w$1=\text{'})$;

w$2=$input$(\text{'}$weight w$2=\text{'})$;

w$3=$input$(\text{'}$Weight w$3=\text{'})$;

w$4=$input$(\text{'}$weight w$4=\text{'})$;

v$1=$input$(\text{'}$weight v$1=\text{'})$;

v$2=$input$(\text{'}$weight v$2=\text{'})$;

disp$(\text{'}$Enter Threshold Value'$)$;

theta$=$input$(\text{'}$theta$=\text{'})$;

x$1=[0011]$;

x$2=[0101]$;

z$=[0110]$;

con$=1$;

while con

zin$1=$x$1*$w$1+$x$2*$w$3$;

zin$2=$x$1*$w$2+$x$2*$w$4$;

for i$=1$:$4$

if zin$1($i$)>=$theta

y$1($i$)=1$;

else

y$1($i$)=0$;

end

if zin$2($i$)>=$theta

y$2($i$)=1$;

else

y$2($i$)=0$;

end

end

yin$=$y$1*$v$1+$y$2*$v$2$;

for i$=1$:$4$

if yin$($i$)>=$theta;

y$($i$)=1$;

else

y$($i$)=0$;

end

end

disp$(\text{'}$Output of Net'$)$;

disp$($y$)$;

if y$==$z

con$=0$;

else

disp$(\text{'}$Net is not learning enter another set of weights and Threshold value'$)$;

w$1=$input$(\text{'}$Weight w$1=\text{'})$;

w$2=$input$(\text{'}$weight w$2=\text{'})$;

w$3=$input$(\text{'}$Weight w$3=\text{'})$;

w$4=$input$(\text{'}$weight w$4=\text{'})$;

v$1=$input$(\text{'}$weight v$1=\text{'})$;

v$2=$input$(\text{'}$weight v$2=\text{'})$;

theta$=$input$(\text{'}$theta$=\text{'})$;

end

end

disp$(\text{'}$McCulloch$-$Pitts Net for XOR function'$)$;

disp$(\text{'}$Weights of Neuron Z$1\text{'})$;

disp$($w$1)$;

disp$($w$3)$;

disp$(\text{'}$weights of Neuron Z$2\text{'})$;

disp$($w$2)$;

disp$($w$4)$;

disp$(\text{'}$weights of Neuron Y$\text{'})$;

disp$($v$1)$;

disp$($v$2)$;

disp$(\text{'}$Threshold value'$)$;

disp$($theta$)$;

$\%$ Enter weights

$\%$ Weight w$1=1$

$\%$ weight w$2=-1$

$\%$ Weight w$3=-1$

$\%$ weight w$4=1$

$\%$ weight v$1=1$

$\%$ weight v$2=1$

$\%$ Enter Threshold Value

$\%$ theta$=1$