Introduction to Deep Learning

Features:

1. Vetorised implementation - Number of layers and number of neurons in a layer are user adjustable
2. Optimizers:
1. Vanilla gradient descent
2. Gradient descent with momentum
3. Gradient descent with Adam
3. Cost functions:
1. L2
2. Cross-Entropy
4. Activations:
   1. Linear
   2. Sigmoid
   3. Relu
   4. Tanh
   5. Weight Initalizers:
1. Xavier
2. He