To get the most out of this book

The prerequisites for the book are basic knowledge of ML or deep learning and intermediate Python skills, although both are not mandatory. We have given a brief introduction to deep learning, touching upon topics such as multi-layer perceptrons, Convolutional Neural Networks (CNNs), and RNNs in Chapter 1, Getting Started. It would be helpful if the reader knows general ML concepts, such as overfitting and model regularization, and classical models, such as linear regression and random forest. In more advanced chapters, the reader might encounter in-depth code walkthroughs that expect at least a basic level of Python programming experience. 

All the code examples in the book can be downloaded from the code book repository as described in the next section. The examples mainly utilize open source tools and open data repositories, and were written for Python 3.5 or higher. The major libraries that are extensively used throughout the book are TensorFlow and NLTK. Detailed installation instructions for these packages can be found in Chapter 1, Getting Started, and Chapter 2, Text Classification and POS Tagging Using NLTK, respectively. Though a GPU is not required for the examples to run, it is advisable to have a system that has one. We recommend training models from the second half of the book on a GPU, as more complicated tasks involve bigger models and larger datasets.