Advanced Machine Learning with R

Tackle data analytics and machine learning challenges and build complex applications with R 3.5

Cory Lesmeister, Dr. Sunil Kumar Chinnamgari

• Publisher: Packt Publishing
• Year: 2019
• Print ISBN: 9781838641771
• eBook ISBN: 9781838645748
• Edition: 1
• Topic: Computer Science
• Subtopic: Artificial Intelligence (AI) & Semantics
• Index: Computer Science

Master machine learning techniques with real-world projects that interface TensorFlow with R, H2O, MXNet, and other languages

Key Features

• Gain expertise in machine learning, deep learning and other techniques
• Build intelligent end-to-end projects for finance, social media, and a variety of domains
• Implement multi-class classification, regression, and clustering

Book Description

R is one of the most popular languages when it comes to exploring the mathematical side of machine learning and easily performing computational statistics.

This Learning Path shows you how to leverage the R ecosystem to build efficient machine learning applications that carry out intelligent tasks within your organization. You'll tackle realistic projects such as building powerful machine learning models with ensembles to predict employee attrition. You'll explore different clustering techniques to segment customers using wholesale data and use TensorFlow and Keras-R for performing advanced computations. You'll also be introduced to reinforcement learning along with its various use cases and models. Additionally, it shows you how some of these black-box models can be diagnosed and understood.

By the end of this Learning Path, you'll be equipped with the skills you need to deploy machine learning techniques in your own projects.

This Learning Path includes content from the following Packt products:

• R Machine Learning Projects by Dr. Sunil Kumar Chinnamgari
• Mastering Machine Learning with R - Third Edition by Cory Lesmeister

What you will learn

• Develop a joke recommendation engine to recommend jokes that match users' tastes
• Build autoencoders for credit card fraud detection
• Work with image recognition and convolutional neural networks
• Make predictions for casino slot machine using reinforcement learning
• Implement NLP techniques for sentiment analysis and customer segmentation
• Produce simple and effective data visualizations for improved insights
• Use NLP to extract insights for text
• Implement tree-based classifiers including random forest and boosted tree

Who this book is for

If you are a data analyst, data scientist, or machine learning developer this is an ideal Learning Path for you. Each project will help you test your skills in implementing machine learning algorithms and techniques. A basic understanding of machine learning and working knowledge of R programming is necessary to get the most out of this Learning Path.

Image Recognition Using Deep Neural Networks

In 1966, Professor Seymour Papert at MIT conceptualized an ambitious summer project titled The Summer Vision Project. The task for the graduate student was to plug a camera into a computer and enable it to understand what it sees! I am sure it would have been super-difficult for the graduate student to have finished this project, as even today the task remains half complete.

A human being, when they look outside, is able to recognize the objects that they see. Without thinking, they are able to classify a cat as a cat, a dog as a dog, a plant as a plant, an animal as an animal—this is happening because the human brain draws knowledge from its extensive prelearned database. After all, as human beings, we have millions of years' worth of evolutionary context that enables us draw inferences from the thing that we see. Computer vision deals with replicating the human vision processes so as to pass them on to machines and automate them.

This chapter is all about learning the theory and implementation of computer vision through machine learning (ML). We will build a feedforward deep learning network and LeNet to enable handwritten digit recognition. We will also build a project that uses a pretrained Inception-BatchNorm network to identify objects in an image. We will cover the following topics as we progress in this chapter:

• Understanding computer vision
• Achieving computer vision with deep learning
• Introduction to the MNIST dataset
• Implementing a deep learning network for handwritten digit recognition
• Implementing computer vision with pretrained models

Technical requirements

For the projects covered in this chapter, we'll make use of a very popular open dataset called MNIST. We'll use Apache MXNet, a modern open source deep learning software framework to train and deploy the required deep neural networks.

Understanding computer vision

In today's world, we have advanced cameras that are very successful at mimicking how a human eye captures light and color; but image-capturing in the right way is just stage one in the whole image-comprehension aspect. Post image-capturing, we will need to enable technology that interprets what has been captured and build context around it. This is what the human brain does when the eyes see something. Here comes the huge challenge: we all know that computers see images as huge piles of integer values that represent intensities across a spectrum of colors, and of course, computer have no context associated with the image itself. This is where ML comes into play. ML allows us to train a context for a dataset such that it enables computers to understand what objects certain sequences of numbers actually represent.

Computer vision is one of the emerging areas where ML is applied. It can be used for several purposes in various domains, including healthcare, agriculture, insurance, and the automotive industry. The following are some of its most popular applications:

• Detecting diseases from medical images, such as CT scan/MRI scan images
• Identifying crop diseases and soil quality to support a better crop yield
• Identifying oil reserves from satellite images
• Self-driving cars
• Monitoring and managing skin condition for psoriasis patients
• Classifying and distinguishing weeds from crops
• Facial recognition
• Extracting information from personal documents, such as passports and ID cards
• Detecting terrain for drones and airplanes
• Biometrics
• Public surveillance
• Organizing personal photos
• Answering visual questions

This is just the tip of the iceberg. It's not an overstatement to say that there is no domain where we cannot find an application for computer vision. Therefore, computer vision is a key area for ML practitioners to focus on.

2323__perlego_...

Table of contents

• Title Page
• Copyright and Credits
• About Packt
• Contributors
• Preface
• Preparing and Understanding Data
• Linear Regression
• Logistic Regression
• Advanced Feature Selection in Linear Models
• K-Nearest Neighbors and Support Vector Machines
• Tree-Based Classification
• Neural Networks and Deep Learning
• Creating Ensembles and Multiclass Methods
• Cluster Analysis
• Principal Component Analysis
• Association Analysis
• Time Series and Causality
• Text Mining
• Exploring the Machine Learning Landscape
• Predicting Employee Attrition Using Ensemble Models
• Implementing a Jokes Recommendation Engine
• Sentiment Analysis of Amazon Reviews with NLP
• Customer Segmentation Using Wholesale Data
• Image Recognition Using Deep Neural Networks
• Credit Card Fraud Detection Using Autoencoders
• Automatic Prose Generation with Recurrent Neural Networks
• Winning the Casino Slot Machines with Reinforcement Learning
• Creating a Package
• Other Books You May Enjoy