Deep Learning - From Big Data to Artificial Intelligence With R

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.

List 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

About the author

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.

Product details

• Authors: Stephane Tuffery, Stephane (University of Rennes 1 Tuffery, Tuffery Stephane
• Publisher: Wiley, John and Sons Ltd
• Languages: English
• Product format: Hardback
• Released: 08.12.2022
• EAN: 9781119845010
• ISBN: 978-1-119-84501-0
• No. of pages: 544
• Subjects: Natural sciences, medicine, IT, technology > IT, data processing > Application software; Statistik, Informatik, Künstliche Intelligenz, Data Mining, Artificial Intelligence, Deep Learning, Statistics, computer science, Data Mining Statistics, Data Mining & Knowledge Discovery, Data Mining u. Knowledge Discovery