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