Handwritten Digit Recognition

Step 1: Define the Problem & Collect Data

Q: What are you trying to predict?

A: Classify images of handwritten digits into their 10 categories (0 to 9).

Q: What will your input data be?

A: Grayscale images of handwritten digits (28x28 pixels).

Q: What type of problem are you facing?

A: Binary classification

Q: What is the size of your dataset?

A: There are 60,000 training samples and 10,000 test samples.

from keras.datasets import mnist
(train_images, train_labels), (test_images, test_labels) = mnist.load_data()

import matplotlib.pyplot as plt

grid_size = 6
f, axarr = plt.subplots(grid_size, grid_size)
for i in range(grid_size):
    for j in range(grid_size):
        axarr[i, j].imshow(train_images[i * grid_size + j])