What this book covers

Chapter 1, Exploring the Potential of JavaScript, takes a look at the JavaScript programming language, its history, ecosystem, and applicability to ML problems. 

Chapter 2, Data Exploration, discusses the data that underlies and powers every ML algorithm, and the various things you can do to preprocess and prepare your data for an ML application. 

Chapter 3, A Tour of Machine Learning Algorithms, takes you on a brief tour of the ML landscape, partitioning it into categories and families of algorithms, much as the gridlines on a map help you navigate unfamiliar terrain. 

Chapter 4, Grouping with Clustering Algorithms, implements our first ML algorithms, with a focus on clustering algorithms that automatically discover and identify patterns within data in order to group similar items together. 

Chapter 5, Classification Algorithms, discusses a broad family of ML algorithms that are used to automatically classify data points with one or more labels, such as spam/not spam, positive or negative sentiment, or any number of arbitrary categories. 

Chapter 6, Association Rule Algorithms, looks at several algorithms used to make associations between data points based on frequency of co-occurrence, such as products that are often bought together on e-commerce stores. 

Chapter 7, Forecasting with Regression Algorithms, looks at time series data, such as server load or stock prices, and discusses various algorithms that can be used to analyze patterns and make predictions for the future.

Chapter 8, Artificial Neural Network Algorithms, teaches you the foundations of neural networks, including their core concepts, architecture, training algorithms, and implementations.

Chapter 9, Deep Neural Networks, digs deeper into neural networks and explores various exotic topologies that can solve problems such as image recognition, computer vision, speech recognition, and language modeling. 

Chapter 10, Natural Language Processing in Practice, discusses the overlap of natural language processing with ML. You learn several common techniques and tactics that you can use when applying machine learning to natural language tasks.  

Chapter 11, Using Machine Learning in Real-Time Applications, discusses various practical approaches to deploying ML applications on production environments, with a particular focus on the data pipeline process.

Chapter 12, Choosing the Best Algorithm for Your Application, goes back to the basics and discusses the things you must consider in the first stages of a ML project, with a particular focus on choosing the best algorithm or set of algorithms for a given application.