Part 2: Error Analysis and Performance Improvements Based on the neural network, you should recommend some next steps in this part. Some ideas include investigating where the model fails to predict and/or trying to improve the model performance through, for example, different activation functions, expanding the network complexity. Notice that you are expected to write some codes in addition to writing an essay It is crucial to provide reasoning behind what you do incorporate code and visual aids like graphs to support your methodologies # Add your code and provide some discussions. Please feel free to add more cells Python/nThis is the main part of this exercise. You must not change the definition of the function. In fact, the comments are going to help you go through the implementation and they are all you need 1.1 Initialize the parameter in the neural network 5 A 6 °C ht rain # Initialize the parameters in the neural network # Based on the figure above, we need the weight and bias matrices. # W1, b1 are the matrices for the first layer # W2, b2 are the matrices for the second layer # You should think about the sizes of the matrices # then initialize elements in the matrix to be random numbers between -0.5 to +0.5 def init_params(): (A) 0 1 W1 = # Your code here b1 = # Your code here W2 = # Your code here b2 = # Your code here return W1, b1, W2, b2 Q Search ENG b IN Python 17:44 24-06-2024 Go Live D PRE/nExercise 1 In this Exercise, we will be developing a basic neural network from the ground up to classify various types of fashion items. The primary objective of this project is to gain a comprehensive understanding of neural network architecture, including its theory and implementation details. Part 0: Initialization To start, let's load some packages and the dataset # Notice that you don't need any other packages. Dont use pre-existing packages such as TensorFlow or Scikit-Learn. import numpy as np import pandas as pd ww import random from matplotlib import pyplot as plt Python

Fig: 1

Fig: 2

Fig: 3