Take a look at Deep Learning concepts with Keras by analysing an image recognition project and learning to develop the model from start to finish.
Examine the business needs of a project and design a solution, create a multi layer network and get an intro to some more sophisticated practices including implementing different types of networks for image recognition, using dropouts and random noise to improve results, and select the proper architecture.
DL Basics
The Perceptron
Feedforward Neural Networks
Lab 2: Implement and train a feed-forward neural network in Keras
Tackling the problem of facial expression recognition
Recurrent Neural Networks
Lab 4: Implementing RNNs using Keras
Implementing and training RNNs using LSTM units on a simple natural language processing task