Building Deep Learning Models

This chapter illustrates how to build deep learning models, their training and evaluation using the Keras framework in a simple and concise way. Some of the concepts behind these models are briefly explained so as to give the reader smooth entry into each section while concentrating mainly of how-to-use rather than details of algorithms themselves. The entry point is shallow networks, upon which the deep neural networks are developed. The is then followed by a touch on Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNNs) and finally Long Short-Term Memory (LSTM)/ Gated Recurring Units (GRUs). Along the way, we provide step-by-step examples on how each of these models can be used in order to cement the ideas behind them. After that we give a quick dive into the Keras library and some references for further investigation. Finally, some self-evaluation exercises are given to emphasize the key takeaways from the chapter. We also provide a list of references for further reading.