MNIST_Classifier

A multi-layer perceptron (MLP) neural network to classify hand-written digits in MNIST dataset

This dataset consists of four files:

1. Training set images, which contains 60,000 28 × 28 grayscale training images, each representing a single handwritten digit.
2. Training set labels, which contains the associated 60,000 labels for the training images.
3. Test set images, which contains 10,000 28 × 28 grayscale testing images, each representing a single handwritten digit.
4. Test set labels, which contains the associated 10,000 labels for the testing images.

program will take three input files and produce one output file as follows: run your_program train_image.csv train_label.csv test_image.csv ⇒ test_predictions.csv