Deep Network basics

In this project I implemented a two layer neural network for a binary classifier and a multi layer neural network for a multiclass classifier.

Two layer neural network for a binary classifier

link to repository

Dataset: MNIST - digits 2 and 3.
Training a two layer network (1 hidden layer dimension=500) for binary classification. Train with the following parameters.
learning rate = 0.1
num iterations = 1000
Filename - twoLayerBinaryClassifier.py
Plot of train error vs iterations;

Multi-layer neural network for multi-class classifier

link to repository

Dataset: MNIST - digits 0 to 9
Training a multi-layer neural network to classify MNIST. The MNIST dataset has 60,000 images which is too large. Therefore, training with just 6000 samples and tested with 1000 samples.
learning rate = 0.1
num iterations = 1000
Filename - deepMultiClassClassifierNetwork.py

  To create a network with 2 hidden layers of dimensions 800 and 500 
    Run the program as:
        python deepMultiClassNetwork starter.py "[784,800,500]"
    The network will have the dimensions [784,800,500,10]
    784 is the input size of digit images (28pix x 28pix = 784)
    10 is the number of digits

Plot of train error vs iterations;