By the end, you will learn - 

1. The best practices to train and develop test sets and analyze bias/variance for building deep learning applications

2. Be able to use standard neural network techniques such as initialization, L2 and dropout regularization, hyperparameter tuning, batch normalization, and gradient checking

3. Implement and apply a variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence

4. Implement a neural network in TensorFlow