Chapter 1, Getting Started with Deep Learning, covers the concepts that will be found in all the subsequent chapters. The basics of machine learning and deep learning are also discussed. We will also look at Deep learning architectures that are distinguished from the more commonplace single-hidden-layer neural networks by their depth, that is, the number of node layers through which data passes in a multistep process of pattern recognition. We will also analyze these architectures with a chart summarizing all the neural networks from where most of the deep learning algorithm evolved. The chapter ends with an analysis of the major deep learning frameworks.

Chapter 2, A First Look at TensorFlow, gives a detailed description of the main TensorFlow features based on a real-life problem, followed by a detailed discussion on TensorFlow installation and configurations. We then look at a computation graph, data, and programming model before getting started with TensorFlow. Toward the end of the chapter, we will look at an example of implementing the linear regression model for predictive analytics.

Chapter 3, Feed-Forward Neural Networks with TensorFlow, demonstrates the theoretical background of different Feed-Forward Neural Networks' (FFNNs) architectures such as Deep Belief Networks (DBNs) and Multilayer Perceptron (MLP). We will then see how to train and analyze the performance metrics that are needed to evaluate the models; also, how to tune the hyperparameters for FFNNs for better and optimized performance. We will also look at two examples using MLP and DBN on how to build very robust and accurate predictive models for predictive analytics on a bank marketing dataset.

Chapter 4, Convolutional Neural Networks, introduces the networks of CNNs that are the basic blocks of a Deep Learning-based image classifier. We will consider the most important CNN architectures, such as Lenet, AlexNet, Vgg, and Inception with hands-on examples, specifically for AlexNet and Vgg. We will then examine the transfer learning and style learning techniques. We will end the chapter by developing a CNN to train a network on a series of facial images to classify their emotional stretch.

Chapter 5, Optimizing TensorFlow Autoencoders, provides sound theoretical background on optimizing autoencoders for data denoising and dimensionality reduction. We will then look at how to implement an autoencoder, gradually moving over to more robust autoencoder implementation, such as denoising autoencoders and convolutional autoencoders. Finally, we will look at a real-life example of fraud analytics using an autoencoder.

Chapter 6, Recurrent Neural Networks, provides some theoretical background of RNNs. We will also look at a few examples for implementing predictive models for classification of images, sentiment analysis of movies, and products spam prediction for NLP. Finally, we'll see how to develop predictive models for time series data.

Chapter 7, Heterogeneous and Distributed Computing, shows the fundamental topic to execute TensorFlow models on GPU cards and distributed systems. We will also look at basic concepts with application examples.

Chapter 8, Advanced TensorFlow Programming, gives an overview of the following TensorFlow-based libraries: tf.contrib.learn, Pretty Tensor, TFLearn, and Keras. For each library, we will describe the main features with applications.

Chapter 9, Recommendation Systems using Factorization Machines, provides several examples on how to develop recommendation system for predictive analytics followed by some theoretical background of recommendation systems. We will then look at an example of developing a movie recommendation engine using collaborative filtering and K-means. Considering the limitations of classical approaches, we'll see how to use Neural Factorization Machines for developing more accurate and robust recommendation systems.

Chapter 10, Reinforcement Learning, covers the basic concepts of RL. We will experience the Q-learning algorithm, which is one of the most popular reinforcement learning algorithms. Furthermore, we'll introduce the OpenAI gym framework that is a TensorFlow compatible toolkit for developing and comparing reinforcement learning algorithms. We end the chapter with the implementation of a Deep Q-Learning algorithm to resolve the cart-pole problem.