What this book covers

Chapter 1, Getting Started with Python Machine Learning, introduces the basic idea of machine learning and TensorFlow with a very simple example. Despite its simplicity, it will challenge us with the risk of overfitting.

Chapter 2, Classifying with Real-world Examples, uses real data to explore classification by training a computer to be able to distinguish between different classes of flowers.

Chapter 3, Regression, explains how to use regression to handle data, a classic topic that is still relevant today. You will also learn about advanced regression techniques such as Lasso and ElasticNet.

Chapter 4, Classification I – Detecting Poor Answers, demonstrates how to use the bias-variance trade-off to debug machine learning models, though this chapter is mainly about using logistic regression to ascertain whether a user's answer to a question is good or bad.

Chapter 5, Dimensionality Reduction, explores what other methods exist to help us to downsize data so that it is chewable by our machine learning algorithms.

Chapter 6, Clustering – Finding Related Posts, demonstrates how powerful the bag of words approach is by applying it to find similar posts without really understanding them.

Chapter 7, Recommendations, builds recommendation systems based on customer product ratings. We will also see how to build recommendations from shopping data without the need for ratings data (which users do not always provide).

Chapter 8, Artificial Neural Networks and Deep Learning, deals with the fundamentals and examples of CNN and RNN using TensorFlow.

Chapter 9, Classification II – Sentiment Analysis, explains how Na?ve Bayes works, and how to use it to classify tweets to see whether they are positive or negative.

Chapter 10, Topic Modeling, moves beyond assigning each post to a single cluster to assigning posts to several topics, as real texts can deal with multiple topics.

Chapter 11, Classification III – Music Genre Classification, sets the scene of someone having scrambled our huge music collection, our only hope of creating order being to let a machine learner classify our songs. It turns out that it is sometimes better to trust someone else's expertise to create features ourselves. The chapter also covers the conversion of speech into text.

Chapter 12, Computer Vision, demonstrates how to apply classification in the specific context of handling images by extracting features from data. We also see how these methods can be adapted to find similar images in a collection, and the applications of CNN and GAN using TensorFlow.

Chapter 13, Reinforcement Learning, covers the fundamentals of reinforcement learning and Deep Q networks on Atari game playing.

Chapter 14, Bigger Data, explores some approaches to dealing with larger data by taking advantage of multiple cores or computing clusters. It also introduces cloud computing (using Amazon Web Services as our cloud provider).