O'Reilly logo

Stay ahead with the world's most comprehensive technology and business learning platform.

With Safari, you learn the way you learn best. Get unlimited access to videos, live online training, learning paths, books, tutorials, and more.

Start Free Trial

No credit card required

R Deep Learning Cookbook

Book Description

Powerful, independent recipes to build deep learning models in different application areas using R libraries

About This Book

  • Master intricacies of R deep learning packages such as mxnet & tensorflow
  • Learn application on deep learning in different domains using practical examples from text, image and speech
  • Guide to set-up deep learning models using CPU and GPU
  • Who This Book Is For

    Data science professionals or analysts who have performed machine learning tasks and now want to explore deep learning and want a quick reference that could address the pain points while implementing deep learning. Those who wish to have an edge over other deep learning professionals will find this book quite useful.

    What You Will Learn

  • Build deep learning models in different application areas using TensorFlow, H2O, and MXnet.
  • Analyzing a Deep boltzmann machine
  • Setting up and Analysing Deep belief networks
  • Building supervised model using various machine learning algorithms
  • Set up variants of basic convolution function
  • Represent data using Autoencoders.
  • Explore generative models available in Deep Learning.
  • Discover sequence modeling using Recurrent nets
  • Learn fundamentals of Reinforcement Leaning
  • Learn the steps involved in applying Deep Learning in text mining
  • Explore application of deep learning in signal processing
  • Utilize Transfer learning for utilizing pre-trained model
  • Train a deep learning model on a GPU
  • In Detail

    Deep Learning is the next big thing. It is a part of machine learning. It's favorable results in applications with huge and complex data is remarkable. Simultaneously, R programming language is very popular amongst the data miners and statisticians.

    This book will help you to get through the problems that you face during the execution of different tasks and Understand hacks in deep learning, neural networks, and advanced machine learning techniques. It will also take you through complex deep learning algorithms and various deep learning packages and libraries in R. It will be starting with different packages in Deep Learning to neural networks and structures. You will also encounter the applications in text mining and processing along with a comparison between CPU and GPU performance.

    By the end of the book, you will have a logical understanding of Deep learning and different deep learning packages to have the most appropriate solutions for your problems.

    Style and approach

    Collection of hands-on recipes that would act as your all-time reference for your deep learning needs

    Table of Contents

    1. Preface
      1. What this book covers
      2. What you need for this book
      3. Who this book is for
      4. Conventions
      5. Reader feedback
      6. Customer support
        1. Downloading the color images of this book
        2. Errata
        3. Piracy
        4. Questions
    2. Getting Started
      1. Introduction
      2. Installing R with an IDE
        1. Getting ready
        2. How to do it...
      3. Installing a Jupyter Notebook application
        1. How to do it...
        2. There's more...
      4. Starting with the basics of machine learning in R
        1. How to do it...
        2. How it works...
      5. Setting up deep learning tools/packages in R
        1. How to do it...
      6. Installing MXNet in R
        1. Getting ready
        2. How to do it...
      7. Installing TensorFlow in R
        1. Getting ready
        2. How to do it...
        3. How it works...
        4. See also
      8. Installing H2O in R
        1. Getting ready
        2. How to do it...
        3. How it works...
        4. There's more...
      9. Installing all three packages at once using Docker
        1. Getting ready
        2. How to do it...
        3. There's more...
    3. Deep Learning with R
      1. Starting with logistic regression
        1. Getting ready
        2. How to do it...
      2. Introducing the dataset
        1. Getting ready
        2. How to do it...
      3. Performing logistic regression using H2O
        1. Getting ready
        2. How to do it...
        3. How it works...
        4. See also
      4. Performing logistic regression using TensorFlow
        1. Getting ready
        2. How to do it...
        3. How it works...
      5. Visualizing TensorFlow graphs
        1. Getting ready
        2. How to do it...
        3. How it works...
      6. Starting with multilayer perceptrons
        1. Getting ready
        2. How to do it...
        3. There's more...
        4. See also
      7. Setting up a neural network using H2O
        1. Getting ready
        2. How to do it...
        3. How it works...
      8. Tuning hyper-parameters using grid searches in H2O
        1. Getting ready
        2. How to do it...
        3. How it works...
      9. Setting up a neural network using MXNet
        1. Getting ready
        2. How to do it...
        3. How it works...
      10. Setting up a neural network using TensorFlow
        1. Getting ready
        2. How to do it...
        3. How it works...
        4. There's more...
    4. Convolution Neural Network
      1. Introduction
      2. Downloading and configuring an image dataset
        1. Getting ready
        2. How to do it...
        3. How it works...
        4. See also
      3. Learning the architecture of a CNN classifier
        1. Getting ready
        2. How to do it...
        3. How it works...
      4. Using functions to initialize weights and biases
        1. Getting ready
        2. How to do it...
        3. How it works...
      5. Using functions to create a new convolution layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      6. Using functions to create a new convolution layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      7. Using functions to flatten the densely connected layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      8. Defining placeholder variables
        1. Getting ready
        2. How to do it...
        3. How it works...
      9. Creating the first convolution layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      10. Creating the second convolution layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      11. Flattening the second convolution layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      12. Creating the first fully connected layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      13. Applying dropout to the first fully connected layer
        1. Getting ready
        2. How to do it...
        3. How it works...
      14. Creating the second fully connected layer with dropout
        1. Getting ready
        2. How to do it...
        3. How it works...
      15. Applying softmax activation to obtain a predicted class
        1. Getting ready
        2. How to do it...
      16. Defining the cost function used for optimization
        1. Getting ready
        2. How to do it...
        3. How it works...
      17. Performing gradient descent cost optimization
        1. Getting ready
        2. How to do it...
      18. Executing the graph in a TensorFlow session
        1. Getting ready
        2. How to do it...
        3. How it works...
      19. Evaluating the performance on test data
        1. Getting ready
        2. How to do it...
        3. How it works...
    5. Data Representation Using Autoencoders
      1. Introduction
      2. Setting up autoencoders
        1. Getting ready
        2. How to do it...
      3. Data normalization
        1. Getting ready
          1. Visualizing dataset distribution
        2. How to do it...
          1. How to set up an autoencoder model
          2. Running optimization
      4. Setting up a regularized autoencoder
        1. Getting ready
        2. How to do it...
        3. How it works...
      5. Fine-tuning the parameters of the autoencoder
      6. Setting up stacked autoencoders
        1. Getting ready
        2. How to do it...
      7. Setting up denoising autoencoders
        1. Getting ready
        2. How to do it...
          1. Reading the dataset
          2. Corrupting data to train
          3. Setting up a denoising autoencoder
        3. How it works...
      8. Building and comparing stochastic encoders and decoders
        1. Getting ready
        2. How to do it...
          1. Setting up a VAE model
          2. Output from the VAE autoencoder
      9. Learning manifolds from autoencoders
        1. How to do it...
          1. Setting up principal component analysis
      10. Evaluating the sparse decomposition
        1. Getting ready
        2. How to do it...
        3. How it works...
    6. Generative Models in Deep Learning
      1. Comparing principal component analysis with the Restricted Boltzmann machine
        1. Getting ready
        2. How to do it...
      2. Setting up a Restricted Boltzmann machine for Bernoulli distribution input
        1. Getting ready
        2. How to do it...
      3. Training a Restricted Boltzmann machine
        1. Getting ready
          1. Example of a sampling
        2. How to do it...
      4. Backward or reconstruction phase of RBM
        1. Getting ready
        2. How to do it...
      5. Understanding the contrastive divergence of the reconstruction
        1. Getting ready
        2. How to do it...
        3. How it works...
      6. Initializing and starting a new TensorFlow session
        1. Getting ready
        2. How to do it...
        3. How it works...
      7. Evaluating the output from an RBM
        1. Getting ready
        2. How to do it...
        3. How it works...
      8. Setting up a Restricted Boltzmann machine for Collaborative Filtering
        1. Getting ready
        2. How to do it...
      9. Performing a full run of training an RBM
        1. Getting ready
        2. How to do it...
      10. Setting up a Deep Belief Network
        1. Getting ready
        2. How to do it...
        3. How it works...
      11. Implementing a feed-forward backpropagation Neural Network
        1. Getting ready
        2. How to do it...
        3. How it works...
      12. Setting up a Deep Restricted Boltzmann Machine
        1. Getting ready
        2. How to do it...
        3. How it works...
    7. Recurrent Neural Networks
      1. Setting up a basic Recurrent Neural Network
        1. Getting ready
        2. How to do it...
        3. How it works...
      2. Setting up a bidirectional RNN model
        1. Getting ready
        2. How to do it...
      3. Setting up a deep RNN model
        1. How to do it...
      4. Setting up a Long short-term memory based sequence model
        1. How to do it...
        2. How it works...
    8. Reinforcement Learning
      1. Introduction
      2. Setting up a Markov Decision Process
        1. Getting ready
        2. How to do it...
      3. Performing model-based learning
        1. How to do it...
      4. Performing model-free learning
        1. Getting ready
        2. How to do it...
    9. Application of Deep Learning in Text Mining
      1. Performing preprocessing of textual data and extraction of sentiments
        1. How to do it...
        2. How it works...
      2. Analyzing documents using tf-idf
        1. How to do it...
        2. How it works...
      3. Performing sentiment prediction using LSTM network
        1. How to do it...
        2. How it works...
      4. Application using text2vec examples
        1. How to do it...
        2. How it works...
    10. Application of Deep Learning to Signal processing
      1. Introducing and preprocessing music MIDI files
        1. Getting ready
        2. How to do it...
      2. Building an RBM model
        1. Getting ready
        2. How to do it...
      3. Generating new music notes
        1. How to do it...
    11. Transfer Learning
      1. Introduction
      2. Illustrating the use of a pretrained model
        1. Getting ready
        2. How to do it...
      3. Setting up the Transfer Learning model
        1. Getting ready
        2. How to do it...
      4. Building an image classification model
        1. Getting ready
        2. How to do it...
      5. Training a deep learning model on a GPU
        1. Getting ready
        2. How to do it...
      6. Comparing performance using CPU and GPU
        1. Getting ready
        2. How to do it...
        3. There's more...
        4. See also