product iamge

Deep Learning: From Big Data to Artificial Intelligence with R

This document was uploaded by one of our users. The uploader already confirmed that they had the permission to publish it. If you are author/publisher or own the copyright of this documents, please report to us by using this DMCA report form.

Download
Search on Amazon

Simply click on the Download Book button.

Yes, Book downloads on Ebookily are 100% Free.

Sometimes the book is free on Amazon As well, so go ahead and hit "Search on Amazon"

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(s): Stephane S. Tuffery
Publisher: Wiley
Year: 2022

Language: English
Pages: 540
City: Hoboken

Cover
Title Page
Copyright
Contents
Acknowledgements
Introduction
Chapter 1 From Big Data to Deep Learning
1.1 Introduction
1.2 Examples of the Use of Big Data and Deep Learning
1.3 Big Data and Deep Learning for Companies and Organizations
1.3.1 Big Data in Finance
1.3.1.1 Google Trends
1.3.1.2 Google Trends and Stock Prices
1.3.1.3 The quantmod Package for Financial Analysis
1.3.1.4 Google Trends in R
1.3.1.5 Matching Data from quantmod and Google Trends
1.3.2 Big Data and Deep Learning in Insurance
1.3.3 Big Data and Deep Learning in Industry
1.3.4 Big Data and Deep Learning in Scientific Research and Education
1.3.4.1 Big Data in Physics and Astrophysics
1.3.4.2 Big Data in Climatology and Earth Sciences
1.3.4.3 Big Data in Education
1.4 Big Data and Deep Learning for Individuals
1.4.1 Big Data and Deep Learning in Healthcare
1.4.1.1 Connected Health and Telemedicine
1.4.1.2 Geolocation and Health
1.4.1.3 The Google Flu Trends
1.4.1.4 Research in Health and Medicine
1.4.2 Big Data and Deep Learning for Drivers
1.4.3 Big Data and Deep Learning for Citizens
1.4.4 Big Data and Deep Learning in the Police
1.5 Risks in Data Processing
1.5.1 Insufficient Quantity of Training Data
1.5.2 Poor Data Quality
1.5.3 Non‐Representative Samples
1.5.4 Missing Values in the Data
1.5.5 Spurious Correlations
1.5.6 Overfitting
1.5.7 Lack of Explainability of Models
1.6 Protection of Personal Data
1.6.1 The Need for Data Protection
1.6.2 Data Anonymization
1.6.3 The General Data Protection Regulation
1.7 Open Data
Notes
Chapter 2 Processing of Large Volumes of Data
2.1 Issues
2.2 The Search for a Parsimonious Model
2.3 Algorithmic Complexity
2.4 Parallel Computing
2.5 Distributed Computing
2.5.1 MapReduce
2.5.2 Hadoop
2.5.3 Computing Tools for Distributed Computing
2.5.4 Column‐Oriented Databases
2.5.5 Distributed Architecture and “Analytics”
2.5.6 Spark
2.6 Computer Resources
2.6.1 Minimum Resources
2.6.2 Graphics Processing Units (GPU) and Tensor Processing Units (TPU)
2.6.3 Solutions in the Cloud
2.7 R and Python Software
2.8 Quantum Computing
Notes
Chapter 3 Reminders of Machine Learning
3.1 General
3.2 The Optimization Algorithms
3.3 Complexity Reduction and Penalized Regression
3.4 Ensemble Methods
3.4.1 Bagging
3.4.2 Random Forests
3.4.3 Extra‐Trees
3.4.4 Boosting
3.4.5 Gradient Boosting Methods
3.4.6 Synthesis of the Ensemble Methods
3.5 Support Vector Machines
3.6 Recommendation Systems
Notes
Chapter 4 Natural Language Processing
4.1 From Lexical Statistics to Natural Language Processing
4.2 Uses of Text Mining and Natural Language Processing
4.3 The Operations of Textual Analysis
4.3.1 Textual Data Collection
4.3.2 Identification of the Language
4.3.3 Tokenization
4.3.4 Part‐of‐Speech Tagging
4.3.5 Named Entity Recognition
4.3.6 Coreference Resolution
4.3.7 Lemmatization
4.3.8 Stemming
4.3.9 Simplifications
4.3.10 Removal of Stop Words
4.4 Vector Representation and Word Embedding
4.4.1 Vector Representation
4.4.2 Analysis on the Document‐Term Matrix
4.4.3 TF‐IDF Weighting
4.4.4 Latent Semantic Analysis
4.4.5 Latent Dirichlet Allocation
4.4.6 Word Frequency Analysis
4.4.7 Word2Vec Embedding
4.4.8 GloVe Embedding
4.4.9 FastText Embedding
4.5 Sentiment Analysis
Notes
Chapter 5 Social Network Analysis
5.1 Social Networks
5.2 Characteristics of Graphs
5.3 Characterization of Social Networks
5.4 Measures of Influence in a Graph
5.5 Graphs with R
5.6 Community Detection
5.6.1 The Modularity of a Graph
5.6.2 Community Detection by Divisive Hierarchical Clustering
5.6.3 Community Detection by Agglomerative Hierarchical Clustering
5.6.4 Other Methods
5.6.5 Community Detection with R
5.7 Research and Analysis on Social Networks
5.8 The Business Model of Social Networks
5.9 Digital Advertising
5.10 Social Network Analysis with R
5.10.1 Collecting Tweets
5.10.2 Formatting the Corpus
5.10.3 Stemming and Lemmatization
5.10.4 Example
5.10.5 Clustering of Terms and Documents
5.10.6 Opinion Scoring
5.10.7 Graph of Terms with Their Connotation
Notes
Chapter 6 Handwriting Recognition
6.1 Data
6.2 Issues
6.3 Data Processing
6.4 Linear and Quadratic Discriminant Analysis
6.5 Multinomial Logistic Regression
6.6 Random Forests
6.7 Extra‐Trees
6.8 Gradient Boosting
6.9 Support Vector Machines
6.10 Single Hidden Layer Perceptron
6.11 H2O Neural Network
6.12 Synthesis of “Classical” Methods
Notes
Chapter 7 Deep Learning
7.1 The Principles of Deep Learning
7.2 Overview of Deep Neural Networks
7.3 Recall on Neural Networks and Their Training
7.4 Difficulties of Gradient Backpropagation
7.5 The Structure of a Convolutional Neural Network
7.6 The Convolution Mechanism
7.7 The Convolution Parameters
7.8 Batch Normalization
7.9 Pooling
7.10 Dilated Convolution
7.11 Dropout and DropConnect
7.12 The Architecture of a Convolutional Neural Network
7.13 Principles of Deep Network Learning for Computer Vision
7.14 Adaptive Learning Algorithms
7.15 Progress in Image Recognition
7.16 Recurrent Neural Networks
7.17 Capsule Networks
7.18 Autoencoders
7.19 Generative Models
7.19.1 Generative Adversarial Networks
7.19.2 Variational Autoencoders
7.20 Other Applications of Deep Learning
7.20.1 Object Detection
7.20.2 Autonomous Vehicles
7.20.3 Analysis of Brain Activity
7.20.4 Analysis of the Style of a Pictorial Work
7.20.5 Go and Chess Games
7.20.6 Other Games
Notes
Chapter 8 Deep Learning for Computer Vision
8.1 Deep Learning Libraries
8.2 MXNet
8.2.1 General Information about MXNet
8.2.2 Creating a Convolutional Network with MXNet
8.2.3 Model Management with MXNet
8.2.4 CIFAR‐10 Image Recognition with MXNet
8.3 Keras and TensorFlow
8.3.1 General Information about Keras
8.3.2 Application of Keras to the MNIST Database
8.3.3 Application of Pre‐Trained Models
8.3.4 Explain the Prediction of a Computer Vision Model
8.3.5 Application of Keras to CIFAR‐10 Images
8.3.6 Classifying Cats and Dogs
8.4 Configuring a Machine's GPU for Deep Learning
8.4.1 Checking the Compatibility of the Graphics Card
8.4.2 NVIDIA Driver Installation
8.4.3 Installation of Microsoft Visual Studio
8.4.4 NVIDIA CUDA Toolkit Installation
8.4.5 Installation of cuDNN
8.5 Computing in the Cloud
8.6 PyTorch
8.6.1 The Python PyTorch Package
8.6.2 The R torch Package
Notes
Chapter 9 Deep Learning for Natural Language Processing
9.1 Neural Network Methods for Text Analysis
9.2 Text Generation Using a Recurrent Neural Network LSTM
9.3 Text Classification Using a LSTM or GRU Recurrent Neural Network
9.4 Text Classification Using a H2O Model
9.5 Application of Convolutional Neural Networks
9.6 Spam Detection Using a Recurrent Neural Network LSTM
9.7 Transformer Models, BERT, and Its Successors
Notes
Chapter 10 Artificial Intelligence
10.1 The Beginnings of Artificial Intelligence
10.2 Human Intelligence and Artificial Intelligence
10.3 The Different Forms of Artificial Intelligence
10.4 Ethical and Societal Issues of Artificial Intelligence
10.5 Fears and Hopes of Artificial Intelligence
10.6 Some Dates of Artificial Intelligence
Notes
Conclusion
Annotated Bibliography
On Big Data and High Dimensional Statistics
On Deep Learning
On Artificial Intelligence
On the Use of R and Python in Data Science and on Big Data
Index
EULA