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

Neural Networks with R

Neural Networks with R

by Balaji Venkateswaran, Giuseppe Ciaburro
Publisher: Packt Publishing
Release Date: September 2017
ISBN: 9781788397872
View table of contents
Start reading

Book Description

Uncover the power of artificial neural networks by implementing them through R code.

About This Book

  • Develop a strong background in neural networks with R, to implement them in your applications
  • Build smart systems using the power of deep learning
  • Real-world case studies to illustrate the power of neural network models

Who This Book Is For

This book is intended for anyone who has a statistical background with knowledge in R and wants to work with neural networks to get better results from complex data. If you are interested in artificial intelligence and deep learning and you want to level up, then this book is what you need!

What You Will Learn

  • Set up R packages for neural networks and deep learning
  • Understand the core concepts of artificial neural networks
  • Understand neurons, perceptrons, bias, weights, and activation functions
  • Implement supervised and unsupervised machine learning in R for neural networks
  • Predict and classify data automatically using neural networks
  • Evaluate and fine-tune the models you build.

In Detail

Neural networks are one of the most fascinating machine learning models for solving complex computational problems efficiently. Neural networks are used to solve wide range of problems in different areas of AI and machine learning.

This book explains the niche aspects of neural networking and provides you with foundation to get started with advanced topics. The book begins with neural network design using the neural net package, then you'll build a solid foundation knowledge of how a neural network learns from data, and the principles behind it. This book covers various types of neural network including recurrent neural networks and convoluted neural networks. You will not only learn how to train neural networks, but will also explore generalization of these networks. Later we will delve into combining different neural network models and work with the real-world use cases.

By the end of this book, you will learn to implement neural network models in your applications with the help of practical examples in the book.

Style and approach

A step-by-step guide filled with real-world practical examples.

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 example code
      2. Errata
      3. Piracy
      4. Questions
  2. Neural Network and Artificial Intelligence Concepts
    1. Introduction
    2. Inspiration for neural networks
    3. How do neural networks work?
    4. Layered approach
    5. Weights and biases
    6. Training neural networks
      1. Supervised learning
      2. Unsupervised learning
    7. Epoch
    8. Activation functions
    9. Different activation functions
      1. Linear function
      2. Unit step activation function
      3. Sigmoid
      4. Hyperbolic tangent
      5. Rectified Linear Unit
    10. Which activation functions to use?
    11. Perceptron and multilayer architectures
    12. Forward and backpropagation
    13. Step-by-step illustration of a neuralnet and an activation function
    14. Feed-forward and feedback networks
    15. Gradient descent
    16. Taxonomy of neural networks
    17. Simple example using R neural net library - neuralnet()
      1. Let us go through the code line-by-line
    18. Implementation using nnet() library
      1. Let us go through the code line-by-line
    19. Deep learning
    20. Pros and cons of neural networks
      1. Pros
      2. Cons
    21. Best practices in neural network implementations
    22. Quick note on GPU processing
    23. Summary
  3. Learning Process in Neural Networks
    1. What is machine learning?
    2. Supervised learning
    3. Unsupervised learning
    4. Reinforcement learning
    5. Training and testing the model
    6. The data cycle
    7. Evaluation metrics
      1. Confusion matrix
        1. True Positive Rate
        2. True Negative Rate
        3. Accuracy
        4. Precision and recall
        5. F-score
        6. Receiver Operating Characteristic curve
    8. Learning in neural networks
    9. Back to backpropagation
    10. Neural network learning algorithm optimization
    11. Supervised learning in neural networks
      1. Boston dataset
      2. Neural network regression with the Boston dataset
    12. Unsupervised learning in neural networks 
      1. Competitive learning
      2. Kohonen SOM
    13. Summary
  4. Deep Learning Using Multilayer Neural Networks
    1. Introduction of DNNs
    2. R for DNNs
    3. Multilayer neural networks with neuralnet
    4. Training and modeling a DNN using H2O
    5. Deep autoencoders using H2O
    6. Summary
  5. Perceptron Neural Network Modeling – Basic Models
    1. Perceptrons and their applications
    2. Simple perceptron – a linear separable classifier
    3. Linear separation
    4. The perceptron function in R
    5. Multi-Layer Perceptron
    6. MLP R implementation using RSNNS
    7. Summary
  6. Training and Visualizing a Neural Network in R
    1. Data fitting with neural network
      1. Exploratory analysis
      2. Neural network model
    2. Classifing breast cancer with a neural network
      1. Exploratory analysis
      2. Neural network model
      3. The network training phase
      4. Testing the network
    3. Early stopping in neural network training
    4. Avoiding overfitting in the model
    5. Generalization of neural networks
    6. Scaling of data in neural network models
    7. Ensemble predictions using neural networks
    8. Summary
  7. Recurrent and Convolutional Neural Networks
    1. Recurrent Neural Network
    2. The rnn package in R
    3. LSTM model
    4. Convolutional Neural Networks
      1. Step #1 – filtering
      2. Step #2 – pooling
      3. Step #3 – ReLU for normalization
      4. Step #4 – voting and classification in the fully connected layer
    5. Common CNN architecture - LeNet
    6. Humidity forecast using RNN
    7. Summary
  8. Use Cases of Neural Networks – Advanced Topics
    1. TensorFlow integration with R
    2. Keras integration with R
    3. MNIST HWR using R
    4. LSTM using the iris dataset
    5. Working with autoencoders
    6. PCA using H2O
    7. Autoencoders using H2O
    8. Breast cancer detection using darch
    9. Summary