This is the second course of total five courses for obtaining "Deep Learning Specialization" on "Coursera" platform by Andrew Ng which is provided by "deeplearning.ai".

Rather than the deep learning being a black box, this course explains what drives performance and how to get good results with industry best-practices.

This course explain the low level concept of:

1. Effective uses of the common neural network "tricks", including initialization, L2 and dropout regularization, Batch normalization, gradient checking.
2. Application of variety of optimization algorithms, such as mini-batch gradient descent, Momentum, RMSprop and Adam, and check for their convergence.
3. The best-practices for the deep learning era how to set up train/dev/test sets and analyze bias/variance

Besides this course also includes application of neural networks in TensorFlow as well as with raw code.

Verify the certificate here.