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

Description

A definitive guide to creating an intelligent web application with the best of machine learning and JavaScript Key FeaturesSolve complex computational problems in browser with JavaScriptTeach your browser how to learn from rules using the power of machine learningUnderstand discoveries on web interface and API in machine learningBook 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 learnGet an overview of state-of-the-art machine learningUnderstand the pre-processing of data handling, cleaning, and preparationLearn Mining and Pattern Extraction with JavaScriptBuild your own model for classification, clustering, and predictionIdentify the most appropriate model for each type of problemApply machine learning techniques to real-world applicationsLearn how JavaScript can be a powerful language for machine learningWho 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 ContentsExploring the potential of JavascriptData ExplorationTour of machine learning algorithmsGrouping with Clustering AlgorithmsIdentify patterns with Classification AlgorithmsApplying Association Rule AlgorithmsForecast with Regression AlgorithmsArtificial Neural Network AlgorithmsDeep Neural NetworkNatural Language Processing in practiceUsing Machine Learning on javascript Real-time applicationsChoosing the best algorithm for your application 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