Deep Learning with R, Second Edition

Name: Deep Learning with R, Second Edition
Brand: Manning
Price: 44.27 EUR
Availability: OnlineOnly

Francois Chollet Tomasz Kalinowski J. J. Allaire(Autor*in)

Manning (Verlag)

1. Auflage

Erschienen am 13. September 2022

568 Seiten

E-Book

ePUB mit Adobe-DRM

Systemvoraussetzungen

978-1-63835-078-1 (ISBN)

44,27 €inkl. 7% MwSt.

Systemvoraussetzungen

für ePUB mit Adobe-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Deep learning from the ground up using R and the powerful Keras library!

In Deep Learning with R, Second Edition you will learn:

Deep learning from first principles
Image classification and image segmentation
Time series forecasting
Text classification and machine translation
Text generation, neural style transfer, and image generation

Deep Learning with R, Second Edition shows you how to put deep learning into action. It's based on the revised new edition of François Chollet's bestselling Deep Learning with Python. All code and examples have been expertly translated to the R language by Tomasz Kalinowski, who maintains the Keras and Tensorflow R packages at RStudio. Novices and experienced ML practitioners will love the expert insights, practical techniques, and important theory for building neural networks.

About the technology
Deep learning has become essential knowledge for data scientists, researchers, and software developers. The R language APIs for Keras and TensorFlow put deep learning within reach for all R users, even if they have no experience with advanced machine learning or neural networks. This book shows you how to get started on core DL tasks like computer vision, natural language processing, and more using R.

About the book
Deep Learning with R, Second Edition is a hands-on guide to deep learning using the R language. As you move through this book, you'll quickly lock in the foundational ideas of deep learning. The intuitive explanations, crisp illustrations, and clear examples guide you through core DL skills like image processing and text manipulation, and even advanced features like transformers. This revised and expanded new edition is adapted from Deep Learning with Python, Second Edition by François Chollet, the creator of the Keras library.

What's inside

Image classification and image segmentation
Time series forecasting
Text classification and machine translation
Text generation, neural style transfer, and image generation

About the reader
For readers with intermediate R skills. No previous experience with Keras, TensorFlow, or deep learning is required.

About the author
François Chollet is a software engineer at Google and creator of Keras. Tomasz Kalinowski is a software engineer at RStudio and maintainer of the Keras and Tensorflow R packages. J.J. Allaire is the founder of RStudio, and the author of the first edition of this book.

Table of Contents
1 What is deep learning?
2 The mathematical building blocks of neural networks
3 Introduction to Keras and TensorFlow
4 Getting started with neural networks: Classification and regression
5 Fundamentals of machine learning
6 The universal workflow of machine learning
7 Working with Keras: A deep dive
8 Introduction to deep learning for computer vision
9 Advanced deep learning for computer vision
10 Deep learning for time series
11 Deep learning for text
12 Generative deep learning
13 Best practices for the real world
14 Conclusions

Weitere Details

Personen

Inhalt

Intro
Title Page
Copyright
Preface
Acknowledgments
About This Book
About the Authors
Chapter 1: What Is Deep Learning?
1.1 Artificial Intelligence, Machine Learning, and Deep Learning
Artificial Intelligence
Machine Learning
Learning Rules and Representations from Data
The "Deep" in "Deep Learning"
Understanding How Deep Learning Works, in Three Figures
What Deep Learning Has Achieved So Far
Don't Believe the Short-Term Hype
The Promise of AI
1.2 Before Deep Learning: A Brief History of Machine Learning
Probabilistic Modeling
Early Neural Networks
Kernel Methods
Decision Trees, Random Forests, and Gradient-Boosting Machines
Back to Neural Networks
What Makes Deep Learning Different?
The Modern Machine Learning Landscape
1.3 Why Deep Learning? Why Now?
Hardware
Data
Algorithms
A New Wave of Investment
The Democratization of Deep Learning
Will It Last?
Chapter 2: The Mathematical Building Blocks of Neural Networks
2.1 A First Look at a Neural Network
2.2 Data Representations for Neural Networks
Scalars (Rank 0 Tensors)
Vectors (Rank 1 Tensors)
Matrices (Rank 2 Tensors)
Rank 3 and Higher-Rank Tensors
Key Attributes
Manipulating Tensors in R
The Notion of Data Batches
Real-World Examples of Data Tensors
Vector Data
Time-Series Data or Sequence Data
Image Data
Video Data
2.3 The Gears of Neural Networks: Tensor Operations
Element-Wise Operations
Broadcasting
Tensor Product
Tensor Reshaping
Geometric Interpretation of Tensor Operations
A Geometric Interpretation of Deep Learning
2.4 The Engine of Neural Networks: Gradient-Based Optimization
What's a Derivative?
Derivative of a Tensor Operation: The gradient
Stochastic Gradient Descent
Chaining Derivatives: The Backpropagation Algorithm
2.5 Looking Back at Our First Example
Reimplementing our First Example from Scratch in TensorFlow
Running One Training Step
The Full Training Loop
Evaluating the Model
Chapter 3: Introduction to Keras and Tensorflow
3.1 What's Tensorflow?
3.2 What's Keras?
3.3 Keras and Tensorflow: A Brief History
3.4 Python and R Interfaces: A Brief History
3.5 Setting Up A Deep Learning Workspace
Installing Keras and TensorFlow
3.6 First Steps with Tensorflow
Tensorflow Tensors
3.7 Tensor Attributes
Tensor Shape and Reshaping
Tensor Slicing
Tensor Broadcasting
The tf Module
Constant Tensors and Variables
Tensor Operations: Doing Math in TensorFlow
A Second Look at the GradientTape API
An End-to-End Example: A Linear Classifier in Pure TensorFlow
3.8 Anatomy of a Neural Network: Understanding Core Keras Apis
Layers: The Building Blocks of Deep Learning
From Layers to Models
The "Compile" Step: Configuring the Learning Process
Picking a Loss Function
Understanding the fit() Method
Monitoring Loss and Metrics on Validation Data
Inference: Using a Model After Training
Chapter 4: Getting Started with Neural Networks: Classification and Regression
4.1 Classifying Movie Reviews: A Binary Classification Example
The IMDB Dataset
Preparing the Data
Building Your Model
Validating Your Approach
Using a Trained Model to Generate Predictions on New Data
Further Experiments
Wrapping Up
4.2 Classifying Newswires: A Multiclass Classification Example
The Reuters Dataset
Preparing the Data
Building Your Model
Validating Your Approach
Generating Predictions on New Data
A Different Way to Handle the Labels and the Loss
The Importance of Having Sufficiently Large Intermediate Layers
Further Experiments
Wrapping Up
4.3 Predicting House Prices: A Regression Example
The Boston Housing Price Dataset
Preparing the Data 123 Building Your Model
Validating Your Approach Using K-fold Validation
Generating Predictions on New Data
Wrapping Up
Chapter 5: Fundamentals of Machine Learning
5.1 Generalization: The Goal of Machine Learning
Underfitting and Overfitting
The Nature of Generalization in Deep Learning
5.2 Evaluating Machine Learning Models
Training, Validation, and Test Sets
Beating a Common-Sense Baseline
Things to Keep in Mind About Model Evaluation
5.3 Improving Model Fit
Tuning Key Gradient Descent Parameters
Leveraging Better Architecture Priors
Increasing Model Capacity
5.4 Improving Generalization
Dataset Curation
Feature Engineering
Using Early Stopping
Regularizing Your Model
Chapter 6: The Universal Workflow of Machine Learning
6.1 Define The Task
Frame the Problem
Collect a Dataset
Understand Your Data
Choose a Measure of Success
6.2 Develop a Model
Prepare the Data
Choose an Evaluation Protocol
Beat a Baseline
Scale Up: Develop a Model that Overfits
Regularize and Tune Your Model
6.3 Deploy the Model
Explain Your Work to Stakeholders and Set Expectations
Ship an Inference Model
Monitor Your Model in the Wild
Maintain Your Model
Chapter 7: Working with Keras: A Deep Dive
7.1 A Spectrum of Workflows
7.2 Different Ways to Build Keras Models
The Sequential Model
The Functional API
Subclassing the Model Class
Mixing and Matching Different Components
Remember: Use the Right Tool for the Job
7.3 Using Built-In Training and Evaluation Loops
Writing Your Own Metrics
Using Callbacks
Writing Your Own Callbacks
Monitoring and Visualization with Tensorboard
7.4 Writing Your Own Training and Evaluation Loops
Training vs. Inference
Low-Level Usage of Metrics
A Complete Training and Evaluation Loop
Make It Fast with tf_function()
Leveraging fit() with a Custom Training Loop
Chapter 8: Introduction to Deep Learning for Computer Vision
8.1 Introduction to Convnets
The Convolution Operation
The Max-Pooling Operation
8.2 Training a Convnet from Scratch on a Small Dataset
The Relevance of Deep Learning for Small Data Problems
Downloading the Data
Building the Model
Data Preprocessing
Using Data Augmentation
8.3 Leveraging a Pretrained Model
Feature Extraction with a Pretrained Model
Fine-Tuning a Pretrained Model
Chapter 9: Advanced Deep Learning for Computer Vision
9.1 Three Essential Computer Vision Tasks
9.2 An Image Segmentation Example
9.3 Modern Convnet Architecture Patterns
Modularity, Hierarchy, and Reuse
Residual Connections
Batch Normalization
Depthwise Separable Convolutions
Putting It Together: A Mini Xception-Like Model
9.4 Interpreting What Convnets Learn
Visualizing Intermediate Activations
Visualizing Convnet Filters
Visualizing Heatmaps of Class Activation
Chapter 10: Deep Learning for Time Series
10.1 Different Kinds of Time-Series Tasks
10.2 A Temperature-Forecasting Example
Preparing the Data
A Common-Sense, Non-Machine Learning Baseline
Let's Try a Basic Machine Learning Model
Let's Try a 1D Convolutional Model
A First Recurrent Baseline
10.3 Understanding Recurrent Neural Networks
A Recurrent Layer in Keras
10.4 Advanced Use of Recurrent Neural Networks
Using Recurrent Dropout to Fight Overfitting
Stacking Recurrent Layers
Using Bidirectional RNNs
Going Even Further
Chapter 11: Deep Learning for Text
11.1 Natural Language Processing: The Bird's-Eye View
11.2 Preparing Text Data
Text Standardization
Text Splitting (Tokenization)
Vocabulary Indexing
Using layer_text_vectorization
11.3 Two Approaches for Representing Groups of Words: Sets and Sequences
Preparing the IMDB Movie Reviews Data
Processing Words as a Set: The Bag-of-Words Approach
Processing Words as a Sequence: The Sequence Model Approach
11.4 The Transformer Architecture
Understanding Self-Attention
Multi-Head Attention
The Transformer Encoder
When to Use Sequence Models Over Bag-of-Words Models
11.5 Beyond Text Classification: Sequence-to-Sequence Learning
A machine Translation Example
Sequence-to-Sequence Learning with RNNs
Sequence-to-Sequence Learning with Transformer
Chapter 12: Generative Deep Learning
12.1 Text Generation
A Brief History of Generative Deep Learning for Sequence Generation
How do you Generate Sequence Data?
The Importance of the Sampling Strategy
Implementing Text Generation with Keras
A Text-Generation Callback with Variable-Temperature Sampling
Wrapping Up
12.2 Deepdream
Implementing Deepdream in Keras
Wrapping Up
12.3 Neural Style Transfer
The Content Loss
The Style Loss
Neural Style Transfer in Keras
Wrapping Up
12.4 Generating Images with Variational Autoencoders
Sampling from Latent Spaces of Images
Concept Vectors for Image Editing
Variational Autoencoders
Implementing a VAE with Keras
Wrapping Up
12.5 Introduction to Generative Adversarial Networks
A Schematic GAN Implementation
A Bag of Tricks
Getting Our Hands on the Celeba Dataset
The Discriminator
The Generator
The Adversarial Network
Wrapping Up
Chapter 13: Best Practices for the Real World
13.1 Getting the Most Out of Your Models
Hyperparameter Optimization
Model Ensembling
13.2 Scaling-Up Model Training
Speeding Up Training on GPU with Mixed Precision
Multi-GPU Training
TPU Training
Chapter 14: Conclusions
14.1 Key Concepts in Review
Various Approaches to AI
What Makes Deep Learning Special within the Field of Machine Learning
How to Think About Deep Learning
Key Enabling Technologies
The Universal Machine Learning Workflow
Key Network Architectures
The Space of Possibilities
14.2 The Limitations of Deep Learning
The Risk of Anthropomorphizing Machine Learning Models
Automatons vs. Intelligent Agents
Local Generalization vs. Extreme Generalization
The Purpose of Intelligence
Climbing the Spectrum of Generalization
14.3 Setting The Course Toward Greater Generality in AI
On the Importance of Setting the Right Objective: The Shortcut Rule
A New Target
14.4 Implementing Intelligence: The Missing Ingredients
Intelligence as Sensitivity to Abstract Analogies
The Two Poles of Abstraction
The Two Poles of Abstraction
The Missing Half of the Picture
14.5 The Future of Deep Learning
Models as Programs
Machine Learning vs. Program Synthesis
Blending Together Deep Learning and Program Synthesis
Lifelong Learning and Modular Subroutine Reuse
The Long-Term Vision
14.6 Staying Up-to-Date in a Fast-Moving Field
Practice on Real-World Problems Using Kaggle
Read About the Latest Developments on arXiv
Explore the Keras Ecosystem
14.7 Final Words
Appendix: Python Primer for R Users
Index

Systemvoraussetzungen

Als PDF speichern Als Link merken