Book Image

Hands-on Machine Learning with JavaScript

Book Image

Hands-on Machine Learning with JavaScript

Overview of this book

In over 20 years of existence, JavaScript has been pushing beyond the boundaries of web evolution with proven existence on servers, embedded devices, Smart TVs, IoT, Smart Cars, and more. Today, with the added advantage of machine learning research and support for JS libraries, JavaScript makes your browsers smarter than ever with the ability to learn patterns and reproduce them to become a part of innovative products and applications. Hands-on Machine Learning with JavaScript presents various avenues of machine learning in a practical and objective way, and helps implement them using the JavaScript language. Predicting behaviors, analyzing feelings, grouping data, and building neural models are some of the skills you will build from this book. You will learn how to train your machine learning models and work with different kinds of data. During this journey, you will come across use cases such as face detection, spam filtering, recommendation systems, character recognition, and more. Moreover, you will learn how to work with deep neural networks and guide your applications to gain insights from data. By the end of this book, you'll have gained hands-on knowledge on evaluating and implementing the right model, along with choosing from different JS libraries, such as NaturalNode, brain, harthur, classifier, and many more to design smarter applications.
Table of Contents (14 chapters)

Available resources

It is often the case that there is no clear winner discernible from an array of algorithm options. In a sentiment analysis problem, for instance, there are several possible approaches and it is not often clear which to take. You can choose from a Naive Bayes classifier with embedded negations, a Naive Bayes classifier using bigrams, an LSTM RNN, a maximum entropy model, and several other techniques.

If the format and form decision point doesn't help you here—for instance, if you have no requirement for a probabilistic classifier—you can make your decision based on your available resources and performance targets. A Bayesian classifier is lightweight with quick training times, very fast evaluation times, a small memory footprint and comparatively small storage and CPU requirements.

An LSTM RNN, on the other hand, is a sophisticated model...