did-you-know? rent-now

Rent More, Save More! Use code: ECRENTAL

did-you-know? rent-now

Rent More, Save More! Use code: ECRENTAL

5% off 1 book, 7% off 2 books, 10% off 3+ books

9781119845010

Deep Learning From Big Data to Artificial Intelligence with R

by
  • ISBN13:

    9781119845010

  • ISBN10:

    1119845017

  • Edition: 1st
  • Format: Hardcover
  • Copyright: 2022-11-14
  • Publisher: Wiley

Note: Supplemental materials are not guaranteed with Rental or Used book purchases.

Purchase Benefits

  • Free Shipping Icon Free Shipping On Orders Over $35!
    Your order must be $35 or more to qualify for free economy shipping. Bulk sales, PO's, Marketplace items, eBooks and apparel do not qualify for this offer.
  • eCampus.com Logo Get Rewarded for Ordering Your Textbooks! Enroll Now
List Price: $106.66 Save up to $26.66
  • Buy Used
    $80.00
    Add to Cart Free Shipping Icon Free Shipping

    USUALLY SHIPS IN 2-4 BUSINESS DAYS

Summary

DEEP LEARNING

A concise and practical exploration of key topics and applications in data science

In Deep Learning: From Big Data to Artificial Intelligence with R, expert researcher Dr. Stéphane Tufféry delivers an insightful discussion of the applications of deep learning and big data that focuses on practical instructions on various software tools and deep learning methods relying on three major libraries: MXNet, PyTorch, and Keras-TensorFlow. In the book, numerous, up-to-date examples are combined with key topics relevant to modern data scientists, including processing optimization, neural network applications, natural language processing, and image recognition.

This is a thoroughly revised and updated edition of a book originally released in French, with new examples and methods included throughout. Classroom-tested and intuitively organized, Deep Learning: From Big Data to Artificial Intelligence with R offers complimentary access to a companion website that provides R and Python source code for the examples offered in the book. Readers will also find:

  • A thorough introduction to practical deep learning techniques with explanations and examples for various programming libraries
  • Comprehensive explorations of a variety of applications for deep learning, including image recognition and natural language processing
  • Discussions of the theory of deep learning, neural networks, and artificial intelligence linked to concrete techniques and strategies commonly used to solve real-world problems

Perfect for graduate students studying data science, big data, deep learning, and artificial intelligence, Deep Learning: From Big Data to Artificial Intelligence with R will also earn a place in the libraries of data science researchers and practicing data scientists.

Author Biography

Stéphane Tufféry, PhD, is Associate Professor at the University of Rennes 1, France where he teaches courses in data mining, deep learning, and big data methods. He also lectures at the Institute of Actuaries in Paris and has published several books on data mining, deep learning, and big data in English and French.

Table of Contents

Acknowledgements xiii

Introduction xv

1 From Big Data to Deep Learning 1

1.1 Introduction 1

1.2 Examples of the Use of Big Data and Deep Learning 6

1.3 Big Data and Deep Learning for Companies and Organizations 9

1.3.1 Big Data in Finance 10

1.3.1.1 Google Trends 10

1.3.1.2 Google Trends and Stock Prices 11

1.3.1.3 The quantmod Package for Financial Analysis 11

1.3.1.4 Google Trends in R 13

1.3.1.5 Matching Data from quantmod and Google Trends 14

1.3.2 Big Data and Deep Learning in Insurance 18

1.3.3 Big Data and Deep Learning in Industry 18

1.3.4 Big Data and Deep Learning in Scientific Research and Education 20

1.3.4.1 Big Data in Physics and Astrophysics 20

1.3.4.2 Big Data in Climatology and Earth Sciences 21

1.3.4.3 Big Data in Education 21

1.4 Big Data and Deep Learning for Individuals 21

1.4.1 Big Data and Deep Learning in Healthcare 21

1.4.1.1 Connected Health and Telemedicine 21

1.4.1.2 Geolocation and Health 22

1.4.1.3 The Google Flu Trends 23

1.4.1.4 Research in Health and Medicine 26

1.4.2 Big Data and Deep Learning for Drivers 28

1.4.3 Big Data and Deep Learning for Citizens 29

1.4.4 Big Data and Deep Learning in the Police 30

1.5 Risks in Data Processing 32

1.5.1 Insufficient Quantity of Training Data 32

1.5.2 Poor Data Quality 32

1.5.3 Non-Representative Samples 33

1.5.4 Missing Values in the Data 33

1.5.5 Spurious Correlations 34

1.5.6 Overfitting 35

1.5.7 Lack of Explainability of Models 35

1.6 Protection of Personal Data 36

1.6.1 The Need for Data Protection 36

1.6.2 Data Anonymization 38

1.6.3 The General Data Protection Regulation 41

1.7 Open Data 43

Notes 44

2 Processing of Large Volumes of Data 49

2.1 Issues 49

2.2 The Search for a Parsimonious Model 50

2.3 Algorithmic Complexity 51

2.4 Parallel Computing 51

2.5 Distributed Computing 52

2.5.1 MapReduce 53

2.5.2 Hadoop 54

2.5.3 Computing Tools for Distributed Computing 55

2.5.4 Column-Oriented Databases 56

2.5.5 Distributed Architecture and “Analytics" 57

2.5.6 Spark 58

2.6 Computer Resources 60

2.6.1 Minimum Resources 60

2.6.2 Graphics Processing Units (GPU) and Tensor Processing Units (TPU) 61

2.6.3 Solutions in the Cloud 62

2.7 R and Python Software 62

2.8 Quantum Computing 67

Notes 68

3 Reminders of Machine Learning 71

3.1 General 71

3.2 The Optimization Algorithms 74

3.3 Complexity Reduction and Penalized Regression 85

3.4 Ensemble Methods 89

3.4.1 Bagging 89

3.4.2 Random Forests 89

3.4.3 Extra-Trees 91

3.4.4 Boosting 92

3.4.5 Gradient Boosting Methods 97

3.4.6 Synthesis of the Ensemble Methods 100

3.5 Support Vector Machines 100

3.6 Recommendation Systems 105

Notes 108

4 Natural Language Processing 111

4.1 From Lexical Statistics to Natural Language Processing 111

4.2 Uses of Text Mining and Natural Language Processing 113

4.3 The Operations of Textual Analysis 114

4.3.1 Textual Data Collection 115

4.3.2 Identification of the Language 115

4.3.3 Tokenization 116

4.3.4 Part-of-Speech Tagging 117

4.3.5 Named Entity Recognition 119

4.3.6 Coreference Resolution 124

4.3.7 Lemmatization 124

4.3.8 Stemming 129

4.3.9 Simplifications 129

4.3.10 Removal of StopWords 130

4.4 Vector Representation andWord Embedding 132

4.4.1 Vector Representation 132

4.4.2 Analysis on the Document-Term Matrix 133

4.4.3 TF-IDF Weighting 142

4.4.4 Latent Semantic Analysis 144

4.4.5 Latent Dirichlet Allocation 152

4.4.6 Word Frequency Analysis 160

4.4.7 Word2Vec Embedding 162

4.4.8 GloVe Embedding 174

4.4.9 FastText Embedding 176

4.5 Sentiment Analysis 180

Notes 184

5 Social Network Analysis 187

5.1 Social Networks 187

5.2 Characteristics of Graphs 188

5.3 Characterization of Social Networks 189

5.4 Measures of Influence in a Graph 190

5.5 Graphs with R 191

5.6 Community Detection 200

5.6.1 The Modularity of a Graph 201

5.6.2 Community Detection by Divisive Hierarchical Clustering 202

5.6.3 Community Detection by Agglomerative Hierarchical Clustering 203

5.6.4 Other Methods 204

5.6.5 Community Detection with R 205

5.7 Research and Analysis on Social Networks 208

5.8 The Business Model of Social Networks 209

5.9 Digital Advertising 211

5.10 Social Network Analysis with R 212

5.10.1 Collecting Tweets 213

5.10.2 Formatting the Corpus 215

5.10.3 Stemming and Lemmatization 216

5.10.4 Example 217

5.10.5 Clustering of Terms and Documents 225

5.10.6 Opinion Scoring 230

5.10.7 Graph of Terms with Their Connotation 231

Notes 234

6 Handwriting Recognition 237

6.1 Data 237

6.2 Issues 238

6.3 Data Processing 238

6.4 Linear and Quadratic Discriminant Analysis 243

6.5 Multinomial Logistic Regression 245

6.6 Random Forests 246

6.7 Extra-Trees 247

6.8 Gradient Boosting 249

6.9 Support Vector Machines 253

6.10 Single Hidden Layer Perceptron 258

6.11 H2O Neural Network 262

6.12 Synthesis of “Classical” Methods 267

Notes 268

7 Deep Learning 269

7.1 The Principles of Deep Learning 269

7.2 Overview of Deep Neural Networks 272

7.3 Recall on Neural Networks and Their Training 274

7.4 Difficulties of Gradient Backpropagation 284

7.5 The Structure of a Convolutional Neural Network 286

7.6 The Convolution Mechanism 288

7.7 The Convolution Parameters 290

7.8 Batch Normalization 292

7.9 Pooling 293

7.10 Dilated Convolution 295

7.11 Dropout and DropConnect 295

7.12 The Architecture of a Convolutional Neural Network 297

7.13 Principles of Deep Network Learning for Computer Vision 299

7.14 Adaptive Learning Algorithms 301

7.15 Progress in Image Recognition 304

7.16 Recurrent Neural Networks 312

7.17 Capsule Networks 317

7.18 Autoencoders 318

7.19 Generative Models 322

7.19.1 Generative Adversarial Networks 323

7.19.2 Variational Autoencoders 324

7.20 Other Applications of Deep Learning 326

7.20.1 Object Detection 326

7.20.2 Autonomous Vehicles 333

7.20.3 Analysis of Brain Activity 334

7.20.4 Analysis of the Style of a PictorialWork 336

7.20.5 Go and Chess Games 338

7.20.6 Other Games 340

Notes 341

8 Deep Learning for Computer Vision 347

8.1 Deep Learning Libraries 347

8.2 MXNet 349

8.2.1 General Information about MXNet 349

8.2.2 Creating a Convolutional Network with MXNet 350

8.2.3 Model Management with MXNet 361

8.2.4 CIFAR-10 Image Recognition with MXNet 362

8.3 Keras and TensorFlow 367

8.3.1 General Information about Keras 370

8.3.2 Application of Keras to the MNIST Database 371

8.3.3 Application of Pre-Trained Models 375

8.3.4 Explain the Prediction of a Computer Vision Model 379

8.3.5 Application of Keras to CIFAR-10 Images 382

8.3.6 Classifying Cats and Dogs 393

8.4 Configuring a Machine’s GPU for Deep Learning 409

8.4.1 Checking the Compatibility of the Graphics Card 410

8.4.2 NVIDIA Driver Installation 410

8.4.3 Installation of Microsoft Visual Studio 411

8.4.4 NVIDIA CUDA To34olkit Installation 411

8.4.5 Installation of cuDNN 412

8.5 Computing in the Cloud 412

8.6 PyTorch 419

8.6.1 The Python PyTorch Package 419

8.6.2 The R torch Package 425

Notes 431

9 Deep Learning for Natural Language Processing 433

9.1 Neural Network Methods for Text Analysis 433

9.2 Text Generation Using a Recurrent Neural Network LSTM 434

9.3 Text Classification Using a LSTM or GRU Recurrent Neural Network 440

9.4 Text Classification Using a H2O Model 452

9.5 Application of Convolutional Neural Networks 456

9.6 Spam Detection Using a Recurrent Neural Network LSTM 460

9.7 Transformer Models, BERT, and Its Successors 461

Notes 479

10 Artificial Intelligence 481

10.1 The Beginnings of Artificial Intelligence 481

10.2 Human Intelligence and Artificial Intelligence 486

10.3 The Different Forms of Artificial Intelligence 488

10.4 Ethical and Societal Issues of Artificial Intelligence 493

10.5 Fears and Hopes of Artificial Intelligence 496

10.6 Some Dates of Artificial Intelligence 499

Notes 502

Conclusion 505

Note 506

Annotated Bibliography 507

On Big Data and High Dimensional Statistics 507

On Deep Learning 509

On Artificial Intelligence 511

On the Use of R and Python in Data Science and on Big Data 512

Index 515

Supplemental Materials

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

Rewards Program