PLEASE HELP IN PYTHON.

A perceptron is a binary linear classifier used in supervised learning which helps to classify the given input data. According to perceptron learning, the algorithm automatically learns the optimal weight coefficients. The input features are then multiplied with these weights to determine if a neuron fires or not. The perceptron receives multiple input signals, and if the sum of the input signals exceeds a certain threshold, it either outputs a signal or does not return an output. In the context of supervised learning and classification, the perceptron can then be used to predict the class of a sample.

In python, mody the given code which has sections missing below for the self$-$driving section.

import numpy as np

import matplotlib.pyplot as plt

import PIL

from PIL import Image

#Let's first create a function that reads an image and returns its $23$x$23$ binary matrix representation:

def get$\_$matrix$($path$)$:

img $=$ Image.open$($path$).$convert$(\text{'}$LA$\text{'})$

mat$=$np$.$zeros$((23,23))$

for x in range$(23)$:

for y in range $(23)$:

mat$[$y$][$x$]=$img.getpixel$(($x$,$ y$))[0]$

if mat$[$y$][$x$]!=0$:

mat$[$y$][$x$]=1$

return mat

#Now we can read and print our $3$ self$-$driving images:

left$=$get$\_$matrix$(\text{'}$Imagen$1.$png$\text{'})$

plt$.$imshow$($left$,$ cmap$=$"gray"$)$

plt$.$show$()$

straight$=$get$\_$matrix$(\text{'}$Imagen$2.$png$\text{'})$

plt$.$imshow$($straight$,$ cmap$=$"gray"$)$

plt$.$show$()$

right$=$get$\_$matrix$(\text{'}$Imagen$3.$png$\text{'})$

plt$.$imshow$($right$,$ cmap$=$"gray"$)$

plt$.$show$()$

#This is how one of our images looks like when binarized:

for i in range$(23)$:

for j in range $(23)$:

print$($int$($left$[$i$][$j$]),$end $="")$

print$(\text{'}$

$\text{'})$

#Output: $00000000000000000000000$

$00000000000000000000000$

$00000000000000000000000$

$00000000000000000000000$

$00000000000000000000000$

$00000000000000000000000$

$01100000000000000000000$

$00110000000000000000000$

$00011100000000000000000$

$00011110000000000000000$

$00001111000000000000000$

$00000111110000000000000$

$00000011111000000000000$

$00000011111100000000000$

$00000001111110000000000$

$00000001111111000000000$

$00000001111111100000000$

$00000001111111110000000$

$00000001111111110000000$

$00000011111111110000000$

$00000011111111111000000$

$00000011111111111000000$

$00000011111111111000000$

#Now using the code of the first point $($PERCEPTRON$)$ train a neural network that can "drive a car" based on our $3$ images:

#If presented with the image left, it has to respond $[1,0].$ If presented with the image straight, it has to respond $[0,0].$ And, finally, if presented with the image right, it has to respond $[0,1]$

#INSTRUCTIONS: This perceptron network has two neurons and $529(23$x$23)$ inputs. The matrix of patterns P is of size $530$x$3(530$ and not $529$ because you have to add, to each of the $3$ patterns, one more component$=1$ for the bias$).$ The W matrix of weights is of size $2$x$530(2$ neurons of $530$ parameters$)$ and has to be set randomly. The target matrix T is the following:

T$=$np$.$array$([[1,0,0],$

$[0,0,1]])$

#You have to reshape the matrixes left, straight, and right to form the matrix P $($do not forget to add $1$ in the end to each reshaped matrix$)$:

# Modify Your code here

P$.$shape

# Output: $(530,3)$

# Set W randomly:

# Modify Your code here

W$.$shape

# Output: $(2,530)$

# Train in a 'while' loop:

#Modify Your code here

# Print the error:

print$($sum$($sum$($E$)))$

# Output: $0$

# Print the actual output of the network after training:

# Modify Your code here

# Output: array$([[1,0,0],$

$[0,0,1]])$