Book Image

Advanced Deep Learning with R

By : Bharatendra Rai

Book Image

Advanced Deep Learning with R

By: Bharatendra Rai

Overview of this book

Deep learning is a branch of machine learning based on a set of algorithms that attempt to model high-level abstractions in data. Advanced Deep Learning with R will help you understand popular deep learning architectures and their variants in R, along with providing real-life examples for them. This deep learning book starts by covering the essential deep learning techniques and concepts for prediction and classification. You will learn about neural networks, deep learning architectures, and the fundamentals for implementing deep learning with R. The book will also take you through using important deep learning libraries such as Keras-R and TensorFlow-R to implement deep learning algorithms within applications. You will get up to speed with artificial neural networks, recurrent neural networks, convolutional neural networks, long short-term memory networks, and more using advanced examples. Later, you'll discover how to apply generative adversarial networks (GANs) to generate new images; autoencoder neural networks for image dimension reduction, image de-noising and image correction and transfer learning to prepare, define, train, and model a deep neural network. By the end of this book, you will be ready to implement your knowledge and newly acquired skills for applying deep learning algorithms in R through real-world examples.

Preface

Who this book is for

What this book covers

To get the most out of this book

Free Chapter

Section 1: Revisiting Deep Learning Basics

Section 1: Revisiting Deep Learning Basics

Revisiting Deep Learning Architecture and Techniques

Revisiting Deep Learning Architecture and Techniques

Deep learning with R

Process of developing a deep network model

Deep learning techniques with R and RStudio

Section 2: Deep Learning for Prediction and Classification

Section 2: Deep Learning for Prediction and Classification

Deep Neural Networks for Multi-Class Classification

Deep Neural Networks for Multi-Class Classification

Cardiotocogram dataset

Preparing the data for model building

Creating and fitting a deep neural network model

Model evaluation and predictions

Performance optimization tips and best practices

Deep Neural Networks for Regression

Deep Neural Networks for Regression

Understanding the Boston Housing dataset

Preparing the data

Creating and fitting a deep neural network model for regression

Model evaluation and prediction

Performance optimization tips and best practices

Section 3: Deep Learning for Computer Vision

Section 3: Deep Learning for Computer Vision

Image Classification and Recognition

Image Classification and Recognition

Handling image data

Data preparation

Creating and fitting the model

Model evaluation and prediction

Performance optimization tips and best practices

Image Classification Using Convolutional Neural Networks

Image Classification Using Convolutional Neural Networks

Data preparation

Layers in the convolutional neural networks

Fitting the model

Model evaluation and prediction

Performance optimization tips and best practices

Applying Autoencoder Neural Networks Using Keras

Applying Autoencoder Neural Networks Using Keras

Types of autoencoders

Dimension reduction autoencoders

Denoising autoencoders

Image correction

Image Classification for Small Data Using Transfer Learning

Image Classification for Small Data Using Transfer Learning

Using a pretrained model to identify an image

Working with the CIFAR10 dataset

Image classification with CNN

Classifying images using the pretrained RESNET50 model

Model evaluation and prediction

Performance optimization tips and best practices

Creating New Images Using Generative Adversarial Networks

Creating New Images Using Generative Adversarial Networks

Generative adversarial network overview

Processing MNIST image data

Developing the generator network

Developing the discriminator network

Training the network

Reviewing results

Performance optimization tips and best practices

Section 4: Deep Learning for Natural Language Processing

Section 4: Deep Learning for Natural Language Processing

Deep Networks for Text Classification

Deep Networks for Text Classification

Preparing the data for model building

Developing deep neural networks

Model evaluation and prediction

Performance optimization tips and best practices

Text Classification Using Recurrent Neural Networks

Text Classification Using Recurrent Neural Networks

Preparing data for model building

Developing a recurrent neural network model

Fitting the model

Model evaluation and prediction

Performance optimization tips and best practices

Text classification Using Long Short-Term Memory Network

Text classification Using Long Short-Term Memory Network

Why do we use LSTM networks?

Preparing text data for model building

Creating a long short-term memory network model

Fitting the LSTM model

Evaluating model performance

Performance optimization tips and best practices

Text Classification Using Convolutional Recurrent Neural Networks

Text Classification Using Convolutional Recurrent Neural Networks

Working with the reuter_50_50 dataset

Preparing the data for model building

Developing the model architecture

Compiling and fitting the model

Evaluating the model and predicting classes

Performance optimization tips and best practices

Section 5: The Road Ahead

Section 5: The Road Ahead

Tips, Tricks, and the Road Ahead

Tips, Tricks, and the Road Ahead

TensorBoard for training performance visualization

Visualizing deep network models with LIME

Visualizing model training with tfruns

Early stopping of network training

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

Fitting the LSTM model

For training the LSTM model, we will use the following code:

# Fit model
model_one <- model %>% fit(train_x, train_y,
         epochs = 10,
         batch_size = 128,
         validation_split = 0.2)
plot(model_one)

We will use train data to fit the LSTM model with ten epochs and use a batch size of 128. We will also reserve 20% of train data as validation data for assessing loss and accuracy values during model training.

Loss and accuracy plot

The following screenshot shows the loss and accuracy plot for model_one:

The plot for loss and accuracy based on training and validation data shows overall closeness between the curves. The observations from the plot are as follows:

There is no major divergence...