What this book covers

Chapter 1, Building Your Own Prediction Models, introduces classification and techniques for evaluation, and then explains decision trees, followed by a coding project in which a predictor for student performance is built.

Chapter 2, Prediction with Random Forests, looks at random forests and uses them in a coding project for classifying bird species.

Chapter 3, Applications for Comment Classification, introduces text processing and the bag-of-words technique. Then shows how this technique can be used to build a spam detector for YouTube comments. Next, you will learn about the sophisticated Word2Vec model and practice it with a coding project that detects positive and negative product, restaurant, and movie reviews.

Chapter 4, Neural Networks, covers a brief introduction to neural networks, proceeds with feedforward neural networks, and looks at a program to identify the genre of a song with neural networks. Finally, you will revise the spam detector from earlier to make it work with neural networks.

Chapter 5, Deep Learning, discusses deep learning and CNNs. You will practice convolutional neural networks and deep learning with two projects. First, you will build a system that can read handwritten mathematical symbols and then revisit the bird species identifier and change the implementation to use a deep convolutional neural network that is significantly more accurate.