Deep Learning with R for Beginners

Book Image

Deep Learning with R for Beginners

By : Mark Hodnett, Joshua F. Wiley, Yuxi (Hayden) Liu, Pablo Maldonado

Book Image

Deep Learning with R for Beginners

By: Mark Hodnett, Joshua F. Wiley, Yuxi (Hayden) Liu, Pablo Maldonado

Overview of this book

Deep learning has a range of practical applications in several domains, while R is the preferred language for designing and deploying deep learning models. This Learning Path introduces you to the basics of deep learning and even teaches you to build a neural network model from scratch. As you make your way through the chapters, you’ll explore deep learning libraries and understand how to create deep learning models for a variety of challenges, right from anomaly detection to recommendation systems. The Learning Path will then help you cover advanced topics, such as generative adversarial networks (GANs), transfer learning, and large-scale deep learning in the cloud, in addition to model optimization, overfitting, and data augmentation. Through real-world projects, you’ll also get up to speed with training convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory networks (LSTMs) in R. By the end of this Learning Path, you’ll be well-versed with deep learning and have the skills you need to implement a number of deep learning concepts in your research work or projects.

Title Page

Copyright and Credits

Copyright and Credits

About Packt

Contributors

Preface

Free Chapter

Getting Started with Deep Learning

Getting Started with Deep Learning

What is deep learning?

A conceptual overview of neural networks

Deep neural networks

Some common myths about deep learning

Setting up your R environment

Training a Prediction Model

Training a Prediction Model

Neural networks in R

The problem of overfitting data – the consequences explained

Use case – building and applying a neural network

Deep Learning Fundamentals

Deep Learning Fundamentals

Building neural networks from scratch in R

Using regularization to overcome overfitting

Use case – improving out-of-sample model performance using dropout

Training Deep Prediction Models

Training Deep Prediction Models

Getting started with deep feedforward neural networks

Activation functions

Introduction to the MXNet deep learning library

Use case – using MXNet for classification and regression

Image Classification Using Convolutional Neural Networks

Image Classification Using Convolutional Neural Networks

Convolutional layers

Image classification using the MXNet library

References/further reading

Tuning and Optimizing Models

Tuning and Optimizing Models

Evaluation metrics and evaluating performance

Data preparation

Data augmentation

Tuning hyperparameters

Use case—using LIME for interpretability

Natural Language Processing Using Deep Learning

Natural Language Processing Using Deep Learning

Document classification

Advanced deep learning text classification

Deep Learning Models Using TensorFlow in R

Deep Learning Models Using TensorFlow in R

Introduction to the TensorFlow library

TensorFlow models

TensorFlow estimators and TensorFlow runs packages

Anomaly Detection and Recommendation Systems

Anomaly Detection and Recommendation Systems

What is unsupervised learning?

How do auto-encoders work?

Training an auto-encoder in R

Using auto-encoders for anomaly detection

Use case – collaborative filtering

Running Deep Learning Models in the Cloud

Running Deep Learning Models in the Cloud

Setting up a local computer for deep learning

Using AWS for deep learning

Using Azure for deep learning

Using Google Cloud for deep learning

Using Paperspace for deep learning

The Next Level in Deep Learning

The Next Level in Deep Learning

Image classification models

Deploying TensorFlow models

Other deep learning topics

Handwritten Digit Recognition using Convolutional Neural Networks

Handwritten Digit Recognition using Convolutional Neural Networks

What is deep learning and why do we need it?

Handwritten digit recognition using CNNs

Traffic Signs Recognition for Intelligent Vehicles

Traffic Signs Recognition for Intelligent Vehicles

How is deep learning applied in self-driving cars?

Traffic sign recognition using CNN

Dealing with a small training set – data augmentation

Reviewing methods to prevent overfitting in CNNs

Fraud Detection with Autoencoders

Fraud Detection with Autoencoders

Our first examples

Credit card fraud detection with autoencoders

Variational Autoencoders

Text fraud detection

Text Generation using Recurrent Neural Networks

Text Generation using Recurrent Neural Networks

What is so exciting about recurrent neural networks?

RNNs from scratch in R

RNN using Keras

Sentiment Analysis with Word Embedding

Sentiment Analysis with Word Embedding

Warm-up – data exploration

Bag of words benchmark

Word embeddings

Sentiment analysis from movie reviews

Mining sentiment from Twitter

Other Books You May Enjoy

Other Books You May Enjoy

Leave a review - let other readers know what you think

Index

Customer Reviews

5 star

0

4 star

0

3 star

0

2 star

0

1 star

0

Our first examples

Let's begin with a few simple examples to understand what is going on.

For some of us, it's very easy to get tempted to try the shiniest algorithms and do hyper-parameter optimization instead of the less glamorous step-by-step understanding.

A simple 2D example

Let's develop our intuition of how the autoencoder works with a simple two-dimensional example.

We first generate 10,000 points coming from a normal distribution with mean 0 and variance 1:

library(MASS)
library(keras)
Sigma <- matrix(c(1,0,0,1),2,2)
n_points <- 10000
df <- mvrnorm(n=n_points, rep(0,2), Sigma)
df <- as.data.frame(df)

The distribution of the values should look as follows:

Distribution of the variable V1 we just generated; the variable V2 looks fairly similar.

Distribution of the variables V1 and V2 we generated.

Let's spice things up a bit and add some outliers to the mixture. In many fraud applications, the fraud rate is about 1–5%, so we generate 1% of our samples as coming from a normal...