Cover......Page 1
Title Page......Page 2
Copyright......Page 3
Credits......Page 5
Foreword......Page 6
About the Author......Page 8
About the Reviewers......Page 9
www.PacktPub.com......Page 11
Customer Feedback......Page 12
Table of Contents......Page 13
Preface......Page 19
Chapter 1: Introduction - Machine Learning and Statistical Science......Page 24
Machine learning in the bigger picture......Page 25
Types of machine learning......Page 27
Supervised learning strategies - regression versus classification......Page 29
Tools of the tradeโprogramming language and libraries......Page 30
The Python language......Page 31
What's matplotlib?......Page 32
Jupyter notebook......Page 33
Mean......Page 35
Variance......Page 37
Standard deviation......Page 38
Random variables and distributions......Page 39
Bernoulli distributions......Page 40
Uniform distribution......Page 42
Normal distribution......Page 43
Logistic distribution......Page 44
Skewness......Page 46
Kurtosis......Page 47
Sliding on the slope......Page 48
Partial derivatives......Page 52
Summary......Page 53
Understanding the problem......Page 54
The ETL process......Page 56
Loading datasets and doing exploratory analysis with SciPy and pandas......Page 57
Working interactively with IPython......Page 58
Working on 2D data......Page 61
Imputation of missing data......Page 63
One hot encoding......Page 64
Normalization or standardization......Page 65
Asking ourselves the right questions......Page 67
Lossย function definition......Page 68
Types of training โ online and batch processing......Page 69
Model implementation and results interpretation......Page 70
Mean squared error......Page 71
Precision score, recall, and F-measure......Page 72
Confusion matrix......Page 73
Homogeneity, completeness, and V-measure......Page 75
Summary......Page 76
References......Page 77
Grouping as a human activity......Page 78
Automating the clustering process......Page 79
Finding a common center - K-means......Page 80
Pros and cons of K-means......Page 83
K-means algorithm breakdown......Page 84
K-means implementations......Page 86
Nearest neighbors......Page 90
Mechanics of K-NN......Page 91
K-NN sample implementation......Page 93
The Elbow method......Page 96
References......Page 98
Regression analysis......Page 99
Applications of regression......Page 100
Quantitative versus qualitative variables......Page 101
Linear regression......Page 102
Determination of the cost function......Page 103
Analytical approach......Page 104
Covariance......Page 105
Correlation......Page 106
Searching for the slope and intercept with covariance and correlation......Page 108
Some intuitive background......Page 110
The gradient descent loop......Page 111
Formalizing our concepts......Page 113
Expressing recursion as a process......Page 115
Going practical โ new tools for new methods......Page 116
Useful diagrams for variable explorations โ pairplot......Page 117
Correlation plot......Page 118
The Iris dataset......Page 119
Getting an intuitive idea with Seaborn pairplot......Page 120
Creating the prediction function......Page 122
Correlation fit......Page 123
Polynomial regression and an introduction toย underfitting and overfitting......Page 124
Linear regression with gradient descent in practice......Page 126
Logistic regression......Page 136
Problem domain of linear regression and logistic regression......Page 137
Logit function......Page 138
The importance of the logit inverse......Page 139
The sigmoid or logistic function......Page 140
Multiclass application โ softmax regression......Page 142
Dataset format......Page 144
Summary......Page 147
References......Page 148
Chapter 5: Neural Networks......Page 149
History of neural models......Page 150
The perceptron model......Page 151
Improving our predictions โ the ADALINE algorithm......Page 153
Limitations of early models......Page 155
Single and multilayer perceptrons......Page 156
MLP origins......Page 157
The chosen optimization algorithm โ backpropagation......Page 158
Implementing a simple function with a single-layer perceptron......Page 161
Representing and understanding the transfer functions......Page 162
Sigmoid or logistic function......Page 163
Playing with the sigmoid......Page 164
Rectified linear unit or ReLU......Page 165
Linear transfer function......Page 166
Defining loss functions for neural networks......Page 167
L1 versus L2 properties......Page 168
Summary......Page 174
References......Page 175
Origin of convolutional neural networks......Page 176
Continuous convolution......Page 178
Discrete convolution......Page 179
Kernels and convolutions......Page 180
Stride and padding......Page 181
Implementing the 2D discrete convolution operation in an example......Page 182
Subsampling operation (pooling)......Page 186
Advantages of the dropout layers......Page 188
Deep convolutional network architectures through time......Page 189
Alexnet......Page 190
The VGG model......Page 191
GoogLenet and the Inception model......Page 192
Batch-normalized inception V2 and V3......Page 193
Residual Networks (ResNet)......Page 194
Detection......Page 195
Segmentation......Page 196
Deploying a deep neural network with Keras......Page 197
Exploring a convolutional network with Quiver......Page 199
Implementing transfer learning......Page 202
References......Page 207
Summary......Page 208
Solving problems with order โย RNNs......Page 209
Development of RNN......Page 210
Training method โ backpropagation through time......Page 211
Main problems of the traditional RNNs โ exploding and vanishing gradients......Page 212
The gate and multiplier operation......Page 213
Part 2 โ set values to keep......Page 216
Part 4 โ output filtered cell state......Page 217
Dataset description and loading......Page 218
Dataset preprocessing......Page 220
References......Page 224
GANs......Page 225
Types of GANย applications......Page 226
Discriminative and generative models......Page 229
Markov decision process......Page 231
Decision elements......Page 232
Optimizing the Markov process......Page 233
Basic RL techniques: Q-learning......Page 234
References......Page 235
Summary......Page 236
Linux installation......Page 237
Installing Anaconda on Linux......Page 238
pip Linux installation method......Page 244
macOS X environment installation......Page 245
Anaconda installation......Page 246
Windows installation......Page 251
Anaconda Windowsย installation......Page 252
Summary......Page 257
Index......Page 259
Index......Page 0