Hands-on Machine Learning with JavaScript: Solve complex computational web problems using machine learning (English Edition)

✍ Scribed by Burak Kanber

• Publisher: Packt Publishing
• Year: 2018
• Tongue: English
• Leaves: 343
• Category: Library

✦ Synopsis

A definitive guide to creating an intelligent web application with the best of machine learning and JavaScript

Key Features

• Solve complex computational problems in browser with JavaScript
• Teach your browser how to learn from rules using the power of machine learning
• Understand discoveries on web interface and API in machine learning

Book Description

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.

What you will learn

• Get an overview of state-of-the-art machine learning
• Understand the pre-processing of data handling, cleaning, and preparation
• Learn Mining and Pattern Extraction with JavaScript
• Build your own model for classification, clustering, and prediction
• Identify the most appropriate model for each type of problem
• Apply machine learning techniques to real-world applications
• Learn how JavaScript can be a powerful language for machine learning

Who This Book Is For

This book is for you if you are a JavaScript developer who wants to implement machine learning to make applications smarter, gain insightful information from the data, and enter the field of machine learning without switching to another language. Working knowledge of JavaScript language is expected to get the most out of the book.

Table of Contents

1. Exploring the potential of Javascript
2. Data Exploration
3. Tour of machine learning algorithms
4. Grouping with Clustering Algorithms
5. Identify patterns with Classification Algorithms
6. Applying Association Rule Algorithms
7. Forecast with Regression Algorithms
8. Artificial Neural Network Algorithms
9. Deep Neural Network
10. Natural Language Processing in practice
11. Using Machine Learning on javascript Real-time applications
12. Choosing the best algorithm for your application

✦ Table of Contents

Cover
Copyright and Credits
Packt Upsell
Contributors
Table of Contents
Preface
Chapter 1: Exploring the Potential of JavaScript
Why JavaScript?
Why machine learning, why now?
Advantages and challenges of JavaScript
The CommonJS initiative
Node.js
TypeScript language
Improvements in ES6
Let and const
Classes
Module imports
Arrow functions
Object literals
The for...of function
Promises
The async/await functions
Preparing the development environment
Installing Node.js
Optionally installing Yarn
Creating and initializing an example project
Creating a Hello World project
Summary
Chapter 2: Data Exploration
An overview
Feature identification
The curse of dimensionality
Feature selection and feature extraction
Pearson correlation example
Cleaning and preparing data
Handling missing data
Missing categorical data
Missing numerical data
Handling noise
Handling outliers
Transforming and normalizing data
Summary
Chapter 3: Tour of Machine Learning Algorithms
Introduction to machine learning
Types of learning
Unsupervised learning
Supervised learning
Measuring accuracy
Supervised learning algorithms
Reinforcement learning
Categories of algorithms
Clustering
Classification
Regression
Dimensionality reduction
Optimization
Natural language processing
Image processing
Summary
Chapter 4: Grouping with Clustering Algorithms
Average and distance
Writing the k-means algorithm
Setting up the environment
Initializing the algorithm
Testing random centroid generation
Assigning points to centroids
Updating centroid locations
The main loop
Example 1 – k-means on simple 2D data
Example 2 – 3D data
k-means where k is unknown
Summary
Chapter 5: Classification Algorithms
k-Nearest Neighbor
Building the KNN algorithm
Example 1 – Height, weight, and gender
Example 2 – Decolorizing a photo
Naive Bayes classifier
Tokenization
Building the algorithm
Example 3 – Movie review sentiment
Support Vector Machine
Random forest
Summary
Chapter 6: Association Rule Algorithms
The mathematical perspective
The algorithmic perspective
Association rule applications
Example – retail data
Summary
Chapter 7: 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
Filtering
Seasonality analysis
Fourier analysis
Summary
Chapter 8: Artificial Neural Network Algorithms
Conceptual overview of neural networks
Backpropagation training
Example - XOR in TensorFlow.js
Summary
Chapter 9: Deep Neural Networks
Convolutional Neural Networks
Convolutions and convolution layers
Example – MNIST handwritten digits
Recurrent neural networks
SimpleRNN
Gated recurrent units
Long Short-Term Memory
Summary
Chapter 10: Natural Language Processing in Practice
String distance
Term frequency - inverse document frequency
Tokenizing
Stemming
Phonetics
Part of speech tagging
Word embedding and neural networks
Summary
Chapter 11: Using Machine Learning in Real-Time Applications
Serializing models
Training models on the server
Web workers
Continually improving and per-user models
Data pipelines
Data querying
Data joining and aggregation
Transformation and normalization
Storing and delivering data
Summary
Chapter 12: 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
Summary
Other Books You May Enjoy
Index