Deep Learning with Python, Second Edition, Video Edition

Deep Learning with Python, Second Edition, Video Edition

by Francois Chollet
Released November 2021
Publisher(s): Manning Publications
ISBN: None

Watch it now on the O’Reilly learning platform with a 10-day free trial.

O’Reilly members get unlimited access to books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.

Start your free trial

Video description

In Video Editions the narrator reads the book while the content, figures, code listings, diagrams, and text appear on the screen. Like an audiobook that you can also watch as a video.

Chollet is a master of pedagogy and explains complex concepts with minimal fuss, cutting through the math with practical Python code. He is also an experienced ML researcher and his insights on various model architectures or training tips are a joy to read.
Martin Görner, Google

Unlock the groundbreaking advances of deep learning with this extensively revised new edition of the bestselling original. Learn directly from the creator of Keras and master practical Python deep learning techniques that are easy to apply in the real world.

In Deep Learning with Python, Second Edition you will learn:
  • Deep learning from first principles
  • Image classification and image segmentation
  • Timeseries forecasting
  • Text classification and machine translation
  • Text generation, neural style transfer, and image generation

Deep Learning with Python has taught thousands of readers how to put the full capabilities of deep learning into action. This extensively revised second edition introduces deep learning using Python and Keras, and is loaded with insights for both novice and experienced ML practitioners. You’ll learn practical techniques that are easy to apply in the real world, and important theory for perfecting neural networks.

about the technology

Recent innovations in deep learning unlock exciting new software capabilities like automated language translation, image recognition, and more. Deep learning is quickly becoming essential knowledge for every software developer, and modern tools like Keras and TensorFlow put it within your reach—even if you have no background in mathematics or data science. This book shows you how to get started.

about the book

Deep Learning with Python, Second Edition introduces the field of deep learning using Python and the powerful Keras library. In this revised and expanded new edition, Keras creator François Chollet offers insights for both novice and experienced machine learning practitioners. As you move through this book, you’ll build your understanding through intuitive explanations, crisp illustrations, and clear examples. You’ll quickly pick up the skills you need to start developing deep-learning applications.

about the audience

For readers with intermediate Python skills. No previous experience with Keras, TensorFlow, or machine learning is required.

about the author

François Chollet is a software engineer at Google and creator of the Keras deep-learning library.

Immerse yourself into this exciting introduction to the topic with lots of real-world examples. A must-read for every deep learning practitioner.
Sayak Paul, Carted

The modern classic just got better.
Edmon Begoli, Oak Ridge National Laboratory

Truly the bible of deep learning.
Yiannis Paraskevopoulos, University of West Attica

NARRATED BY DEREK DYSART

Table of contents

  1. Chapter 1 What is deep learning?
  2. Chapter 1 Learning rules and representations from data
  3. Chapter 1 Understanding how deep learning works, in three figures
  4. Chapter 1 Before deep learning: A brief history of machine learning
  5. Chapter 1 Back to neural networks
  6. Chapter 1 Why deep learning? Why now?
  7. Chapter 1 Algorithms
  8. Chapter 2 The mathematical building blocks of neural networks
  9. Chapter 2 Data representations for neural networks
  10. Chapter 2 Real-world examples of data tensors
  11. Chapter 2 The gears of neural networks: Tensor operations
  12. Chapter 2 Tensor reshaping
  13. Chapter 2 The engine of neural networks: Gradient-based optimization
  14. Chapter 2 Derivative of a tensor operation: The gradient
  15. Chapter 2 Chaining derivatives: The Backpropagation algorithm
  16. Chapter 2 Looking back at our first example
  17. Chapter 3 Introduction to Keras and TensorFlow
  18. Chapter 3 Setting up a deep learning workspace
  19. Chapter 3 First steps with TensorFlow
  20. Chapter 3 Anatomy of a neural network: Understanding core Keras APIs
  21. Chapter 3 The “compile” step: Configuring the learning process
  22. Chapter 4 Getting started with neural networks: Classification and regression
  23. Chapter 4 Building your model
  24. Chapter 4 Classifying newswires: A multiclass classification example
  25. Chapter 4 Predicting house prices: A regression example
  26. Chapter 5 Fundamentals of machine learning
  27. Chapter 5 The nature of generalization in deep learning
  28. Chapter 5 Evaluating machine learning models
  29. Chapter 5 Improving model fit
  30. Chapter 5 Improving generalization
  31. Chapter 5 Regularizing your model
  32. Chapter 6 The universal workflow of machine learning
  33. Chapter 6 Collect a dataset
  34. Chapter 6 Develop a model
  35. Chapter 6 Beat a baseline
  36. Chapter 6 Deploy the model
  37. Chapter 6 Monitor your model in the wild
  38. Chapter 7 Working with Keras: A deep dive
  39. Chapter 7 Subclassing the Model class
  40. Chapter 7 Using built-in training and evaluation loops
  41. Chapter 7 Writing your own training and evaluation loops
  42. Chapter 7 Make it fast with tf.function
  43. Chapter 8 Introduction to deep learning for computer vision
  44. Chapter 8 The convolution operation
  45. Chapter 8 Training a convnet from scratch on a small dataset
  46. Chapter 8 Data preprocessing
  47. Chapter 8 Leveraging a pretrained model
  48. Chapter 8 Feature extraction with a pretrained model
  49. Chapter 9 Advanced deep learning for computer vision
  50. Chapter 9 Modern convnet architecture patterns
  51. Chapter 9 Residual connections
  52. Chapter 9 Depthwise separable convolutions
  53. Chapter 9 Interpreting what convnets learn
  54. Chapter 9 Visualizing convnet filters
  55. Chapter 9 Visualizing heatmaps of class activation
  56. Chapter 10 Deep learning for timeseries
  57. Chapter 10 Preparing the data
  58. Chapter 10 Let’s try a basic machine learning model
  59. Chapter 10 Understanding recurrent neural networks
  60. Chapter 10 A recurrent layer in Keras
  61. Chapter 10 Advanced use of recurrent neural networks
  62. Chapter 10 Using bidirectional RNNs
  63. Chapter 11 Deep learning for text
  64. Chapter 11 Preparing text data
  65. Chapter 11 Vocabulary indexing
  66. Chapter 11 Two approaches for representing groups of words: Sets and sequences
  67. Chapter 11 Processing words as a sequence: The sequence model approach, Part 1
  68. Chapter 11 Processing words as a sequence: The sequence model approach, Part 2
  69. Chapter 11 The Transformer architecture
  70. Chapter 11 The Transformer encoder
  71. Chapter 11 Beyond text classification: Sequence-to-sequence learning
  72. Chapter 11 Sequence-to-sequence learning with Transformer
  73. Chapter 12 Generative deep learning
  74. Chapter 12 How do you generate sequence data?
  75. Chapter 12 A text-generation callback with variable-temperature sampling
  76. Chapter 12 DeepDream
  77. Chapter 12 Neural style transfer
  78. Chapter 12 Generating images with variational autoencoders
  79. Chapter 12 Implementing a VAE with Keras
  80. Chapter 12 A bag of tricks
  81. Chapter 13 Best practices for the real world
  82. Chapter 13 Hyperparameter optimization
  83. Chapter 13 Scaling-up model training
  84. Chapter 13 Multi-GPU training
  85. Chapter 13 TPU training
  86. Chapter 14 Conclusions
  87. Chapter 14 Key enabling technologies
  88. Chapter 14 Key network architectures
  89. Chapter 14 The limitations of deep learning
  90. Chapter 14 Local generalization vs. extreme generalization
  91. Chapter 14 The purpose of intelligence
  92. Chapter 14 Setting the course toward greater generality in AI
  93. Chapter 14 Implementing intelligence: The missing ingredients
  94. Chapter 14 The missing half of the picture
  95. Chapter 14 Blending together deep learning and program synthesis
  96. Chapter 14 Lifelong learning and modular subroutine reuse

Product information

  • Title: Deep Learning with Python, Second Edition, Video Edition
  • Author(s): Francois Chollet
  • Release date: November 2021
  • Publisher(s): Manning Publications
  • ISBN: None