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.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Exploring the Potential of JavaScript

Exploring the Potential of JavaScript

Why JavaScript?

Why machine learning, why now?

Advantages and challenges of JavaScript

The CommonJS initiative

TypeScript language

Improvements in ES6

Preparing the development environment

Data Exploration

Data Exploration

Feature identification

Cleaning and preparing data

Tour of Machine Learning Algorithms

Tour of Machine Learning Algorithms

Introduction to machine learning

Types of learning

Categories of algorithms

Grouping with Clustering Algorithms

Grouping with Clustering Algorithms

Average and distance

Writing the k-means algorithm

Example 1 – k-means on simple 2D data

Example 2 – 3D data

k-means where k is unknown

Classification Algorithms

Classification Algorithms

k-Nearest Neighbor

Naive Bayes classifier

Support Vector Machine

Association Rule Algorithms

Association Rule Algorithms

The mathematical perspective

The algorithmic perspective

Association rule applications

Example – retail data

Forecasting with Regression Algorithms

Forecasting with Regression Algorithms

Regression versus classification

Regression basics

Example 1 – linear regression

Example 2 – exponential regression

Example 3 – polynomial regression

Other time-series analysis techniques

Artificial Neural Network Algorithms

Artificial Neural Network Algorithms

Conceptual overview of neural networks

Backpropagation training

Example - XOR in TensorFlow.js

Deep Neural Networks

Deep Neural Networks

Convolutional Neural Networks

Recurrent neural networks

Natural Language Processing in Practice

Natural Language Processing in Practice

String distance

Term frequency - inverse document frequency

Part of speech tagging

Word embedding and neural networks

Using Machine Learning in Real-Time Applications

Using Machine Learning in Real-Time Applications

Serializing models

Choosing the Best Algorithm for Your Application

Choosing the Best Algorithm for Your Application

Mode of learning

The task at hand

Format, form, input, and output

Available resources

When it goes wrong

Combining models

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Data pipelines

When developing a production ML system, it's not likely that you will have the training data handed to you in a ready-to-process format. Production ML systems are typically part of larger application systems, and the data that you use will probably originate from several different sources. The training set for an ML algorithm may be a subset of your larger database, combined with images hosted on a Content Delivery Network (CDN) and event data from an Elasticsearch server. In our examples, we have been given an isolated training set, but in the real world we will need to generate the training set in an automated and repeatable manner.

The process of ushering data through various stages of a life cycle is called data pipelining. Data pipelining may include data selectors that run SQL or Elasticsearch queries for objects, event subscriptions which allow data...