001 Chapter 1 What is deep learning (79.53 MB)
002 Chapter 1 Before deep learning A brief history of machine learning (47.83 MB)
003 Chapter 1 Why deep learning Why now (36.86 MB)
004 Chapter 2 The mathematical building blocks of neural networks (22.29 MB)
005 Chapter 2 Data representations for neural networks (35.86 MB)
006 Chapter 2 The gears of neural networks Tensor operations (32.98 MB)
007 Chapter 2 The engine of neural networks Gradient-based optimization (63.63 MB)
008 Chapter 2 Looking back at our first example (19.37 MB)
009 Chapter 2 Summary (3.92 MB)
010 Chapter 3 Introduction to Keras and TensorFlow (8.59 MB)
011 Chapter 3 What s Keras (9.04 MB)
012 Chapter 3 Keras and TensorFlow A brief history (5.9 MB)
013 Chapter 3 Python and R interfaces A brief history (2.22 MB)
014 Chapter 3 Setting up a deep learning workspace (11.54 MB)
015 Chapter 3 First steps with TensorFlow (5.09 MB)
016 Chapter 3 Tensor attributes (46.5 MB)
017 Chapter 3 Anatomy of a neural network Understanding core Keras APIs (48.64 MB)
018 Chapter 3 Summary (3.46 MB)
019 Chapter 4 Getting started with neural networks Classification and regression (44.74 MB)
020 Chapter 4 Classifying newswires A multiclass classification example (24.88 MB)
021 Chapter 4 Predicting house prices A regression example (25.84 MB)
022 Chapter 4 Summary (1.79 MB)
023 Chapter 5 Fundamentals of machine learning (50.36 MB)
024 Chapter 5 Evaluating machine learning models (24.29 MB)
025 Chapter 5 Improving model fit (14.73 MB)
026 Chapter 5 Improving generalization (42.72 MB)
027 Chapter 5 Summary (5.51 MB)
028 Chapter 6 The universal workflow of machine learning (55.06 MB)
029 Chapter 6 Develop a model (31.99 MB)
030 Chapter 6 Deploy the model (36.23 MB)
031 Chapter 6 Summary (3.29 MB)
032 Chapter 7 Working with Keras A deep dive (6.06 MB)
033 Chapter 7 Different ways to build Keras models (37.11 MB)
034 Chapter 7 Using built-in training and evaluation loops (29.5 MB)
035 Chapter 7 Writing your own training and evaluation loops (32.42 MB)
036 Chapter 7 Summary (2.76 MB)
037 Chapter 8 Introduction to deep learning for computer vision (43.59 MB)
038 Chapter 8 Training a convnet from scratch on a small dataset (50.91 MB)
039 Chapter 8 Leveraging a pretrained model (41.16 MB)
040 Chapter 8 Summary (2.45 MB)
041 Chapter 9 Advanced deep learning for computer vision (9 MB)
042 Chapter 9 An image segmentation example (27.85 MB)
043 Chapter 9 Modern convnet architecture patterns (68.16 MB)
044 Chapter 9 Interpreting what convnets learn (50.5 MB)
045 Chapter 9 Summary (1.92 MB)
046 Chapter 10 Deep learning for time series (9.38 MB)
047 Chapter 10 A temperature-forecasting example (42.8 MB)
048 Chapter 10 Understanding recurrent neural networks (30.39 MB)
049 Chapter 10 Advanced use of recurrent neural networks (41.18 MB)
050 Chapter 10 Summary (4.04 MB)
051 Chapter 11 Deep learning for text (18.47 MB)
052 Chapter 11 Preparing text data (34.82 MB)
053 Chapter 11 Two approaches for representing groups of words Sets and sequences (77.34 MB)
054 Chapter 11 The Transformer architecture (54.02 MB)
055 Chapter 11 Beyond text classification Sequence-to-sequence learning (51.63 MB)
056 Chapter 11 Summary (4.78 MB)
057 Chapter 12 Generative deep learning (79.33 MB)
058 Chapter 12 DeepDream (23.73 MB)
059 Chapter 12 Neural style transfer (33.91 MB)
060 Chapter 12 Generating images with variational autoencoders (34.39 MB)
061 Chapter 12 Introduction to generative adversarial networks (43.27 MB)
062 Chapter 12 Summary (2.52 MB)
063 Chapter 13 Best practices for the real world (53.81 MB)
064 Chapter 13 Scaling-up model training (48.23 MB)
065 Chapter 13 Summary (2.41 MB)
066 Chapter 14 Conclusions (72.26 MB)
067 Chapter 14 The limitations of deep learning (56.08 MB)
068 Chapter 14 Setting the course toward greater generality in AI (23.02 MB)
069 Chapter 14 Implementing intelligence The missing ingredients (33.7 MB)
070 Chapter 14 The future of deep learning (36.74 MB)
071 Chapter 14 Staying up-to-date in a fast-moving field (13.31 MB)
072 Chapter 14 Final words (1.6 MB)