Deep Neural Network for MNIST Classification
This project uses the MNIST database of handwritten digits to write a deep neural network. The database provides 70,000 images (28x28 pixels) of handwritten digits (1 digit per image). This is a classification problem with 10 classes and the neural network has 2 hidden layers. The goal is to write an algorithm that detects which digit is written (0, 1, 2, 3, 4, 5, 6, 7, 8, 9).