Deep Learning with Python video edition

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.

"The clearest explanation of deep learning I have come was a joy to read."
Richard Tobias, Cephasonics

Deep Learning with Python introduces the field of deep learning using the Python language and the powerful Keras library. Written by Keras creator and Google AI researcher François Chollet, this book builds your understanding through intuitive explanations and practical examples.

Machine learning has made remarkable progress in recent years. We went from near-unusable speech and image recognition, to near-human accuracy. We went from machines that couldn't beat a serious Go player, to defeating a world champion. Behind this progress is deep learning—a combination of engineering advances, best practices, and theory that enables a wealth of previously impossible smart applications.

  • Deep learning from first principles
  • Setting up your own deep-learning environment
  • Image-classification models
  • Deep learning for text and sequences
  • Neural style transfer, text generation, and image generation
This Video Editions book requires intermediate Python skills. No previous experience with Keras, TensorFlow, or machine learning is required.

François Chollet works on deep learning at Google in Mountain View, CA. He is the creator of the Keras deep-learning library, as well as a contributor to the TensorFlow machine-learning framework. He also does deep-learning research, with a focus on computer vision and the application of machine learning to formal reasoning. His papers have been published at major conferences in the field, including the Conference on Computer Vision and Pattern Recognition (CVPR), the Conference and Workshop on Neural Information Processing Systems (NIPS), the International Conference on Learning Representations (ICLR), and others.

An excellent hands-on introductory title, with great depth and breadth.
David Blumenthal-Barby, Babbel

Bridges the gap between the hype and a functioning deep-learning system.
Peter Rabinovitch, Akamai

The best resource for becoming a master of Keras and deep learning.
Claudio Rodriguez, Cox Media Group


Table of contents

    1. Chapter 1. What is deep learning?
    2. Chapter 1. Learning representations from data
    3. Chapter 1. Understanding how deep learning works, in three figures
    4. Chapter 1. Don’t believe the short-term hype
    5. Chapter 1. Before deep learning: a brief history of machine learning
    6. Chapter 1. Decision trees, random forests, and gradient boosting machines
    7. Chapter 1. Why deep learning? Why now?
    8. Chapter 1. A new wave of investment
    9. Chapter 2. Before we begin: the mathematical building blocks of neural networks
    10. Chapter 2. Data representations for neural networks
    11. Chapter 2. Real-world examples of data tensors
    12. Chapter 2. The gears of neural networks: tensor operations
    13. Chapter 2. Tensor dot
    14. Chapter 2. The engine of neural networks: gradient-based optimization
    15. Chapter 2. Stochastic gradient descent
    16. Chapter 2. Looking back at our first example
    17. Chapter 3. Getting started with neural networks
    18. Chapter 3. Introduction to Keras
    19. Chapter 3. Setting up a deep-learning workstation
    20. Chapter 3. Classifying movie reviews: a binary classification example
    21. Chapter 3. Validating your approach
    22. Chapter 3. Classifying newswires: a multiclass classification example
    23. Chapter 3. Predicting house prices: a regression example
    24. Chapter 4. Fundamentals of machine learning
    25. Chapter 4. Evaluating machine-learning models
    26. Chapter 4. Data preprocessing, feature engineering, and feature learning
    27. Chapter 4. Overfitting and underfitting
    28. Chapter 4. Adding weight regularization
    29. Chapter 4. The universal workflow of machine learning
    30. Chapter 4. Developing a model that does better than a baseline
    1. Chapter 5. Deep learning for computer vision
    2. Chapter 5. The convolution operation
    3. Chapter 5. The max-pooling operation
    4. Chapter 5. Training a convnet from scratch on a small dataset
    5. Chapter 5. Data preprocessing
    6. Chapter 5. Using a pretrained convnet
    7. Chapter 5. Fine-tuning
    8. Chapter 5. Visualizing what convnets learn
    9. Chapter 5. Visualizing convnet filters
    10. Chapter 6. Deep learning for text and sequences
    11. Chapter 6. Using word embeddings
    12. Chapter 6. Putting it all together: from raw text to word embeddings
    13. Chapter 6. Understanding recurrent neural networks
    14. Chapter 6. Understanding the LSTM and GRU layers
    15. Chapter 6. Advanced use of recurrent neural networks
    16. Chapter 6. A common-sense, non-machine-learning baseline
    17. Chapter 6. Using recurrent dropout to fight overfitting
    18. Chapter 6. Going even further
    19. Chapter 6. Sequence processing with convnets
    20. Chapter 6. Combining CNNs and RNNs to process long sequences
    21. Chapter 7. Advanced deep-learning best practices
    22. Chapter 7. Multi-input models
    23. Chapter 7. Directed acyclic graphs of layers
    24. Chapter 7. Layer weight sharing
    25. Chapter 7. Inspecting and monitoring deep-learning models using Keras callba- acks and TensorBoard
    26. Chapter 7. Introduction to TensorBoard: the TensorFlow visualization framework
    27. Chapter 7. Getting the most out of your models
    28. Chapter 7. Hyperparameter optimization
    29. Chapter 7. Model ensembling
    30. Chapter 8. Generative deep learning
    31. Chapter 8. A brief history of generative recurrent networks
    32. Chapter 8. Implementing character-level LSTM text generation
    33. Chapter 8. DeepDream
    34. Chapter 8. Neural style transfer
    35. Chapter 8. Neural style transfer in Keras
    36. Chapter 8. Generating images with variational autoencoders
    37. Chapter 8. Variational autoencoders
    38. Chapter 8. Introduction to generative adversarial networks
    39. Chapter 8. A bag of tricks
    40. Chapter 9. Conclusions
    41. Chapter 9. How to think about deep learning
    42. Chapter 9. Key network architectures
    43. Chapter 9. The space of possibilities
    44. Chapter 9. The limitations of deep learning
    45. Chapter 9. Local generalization vs. extreme generalization
    46. Chapter 9. The future of deep learning
    47. Chapter 9. Automated machine learning
    48. Chapter 9. Staying up to date in a fast-moving field

Product information

  • Title: Deep Learning with Python video edition
  • Author(s): François Chollet
  • Release date: November 2017
  • Publisher(s): Manning Publications
  • ISBN: 9781617294433VE