# Artificial Intelligence Assignment (2445 words)

## Transcribed Text

WS-9 Bonus TASK (5 marks) Take random 10 MNIST images, each image is 28 X 28. For each image, create an image vector of 1x784 (i.e. rows of pixels in the image are placed one after the other to form a 1D image) Put all the images together in one big image-matrix, given as: ImageVecl MNIST_ImageMatrix = ImageVec2 ImageVee20 Apply PCA (with 154 components) + explain each of the following in your own words: 2.1. Find eigenvector transformation: FinalData = RowFeatureVector X RowDataAdjust 2.2. Find: RowDataAdjust = RowFeatureVector" X FinalData 2.3. Find: RowOriginalData = (RowFeatureVector² X FinalData) + OriginalM ear 2.4. Compare with 154 (hidden) neurons Autoencoder (From Lecture 8)

## Solution Preview

This material may consist of step-by-step explanations on how to solve a problem or examples of proper writing, including the use of citations, references, bibliographies, and formatting. This material is made available for the sole purpose of studying and learning - misuse is strictly forbidden.

import numpy as np
import matplotlib.pyplot as plt
import scipy.linalg as la

import input_data

mnist = input_data.read_data_sets("MNIST_Data/", one_hot=False)
batch = mnist.train.next_batch(10)

data = batch[0]

for i in range(10):
data[i] = data[i] - np.mean(data[i])

cov_data=np.cov(data)

eig_vec = la.eig(cov_data)

max_arg=np.argmax(eig_vec[0])

max_eig_vec=np.array([eig_vec[1][max_arg]])

max_eig_vec_inv=np.linalg.inv(eig_vec[1])[max_arg]

max_eig_vec_inv = np.reshape(max_eig_vec_inv,(1,10))

final_data = np.matmul(max_eig_vec,data) #eigen vectors...
\$165.00 for this solution

PayPal, G Pay, ApplePay, Amazon Pay, and all major credit cards accepted.

### Find A Tutor

View available Artificial Intelligence Tutors

Get College Homework Help.

Are you sure you don't want to upload any files?

Fast tutor response requires as much info as possible.