دانلود کتاب Deep Learning for Dummies

فهرست مطالب :

Title Page......Page 3
Copyright Page......Page 4
Table of Contents......Page 7
About This Book......Page 15
Foolish Assumptions......Page 16
Icons Used in This Book......Page 17
Beyond the Book......Page 18
Where to Go from Here......Page 19
Part 1 Discovering Deep Learning......Page 21
Chapter 1 Introducing Deep Learning......Page 23
Starting from Artificial Intelligence......Page 24
Considering the role of AI......Page 26
Focusing on machine learning......Page 29
Moving from machine learning to deep learning......Page 30
Understanding the concept of learning......Page 32
Considering the Deep Learning Programming Environment......Page 33
Knowing when not to use deep learning......Page 36
Chapter 2 Introducing the Machine Learning Principles......Page 39
Understanding how machine learning works......Page 40
Understanding that it’s pure math......Page 41
Learning by different strategies......Page 42
Training, validating, and testing data......Page 44
Looking for generalization......Page 45
Getting to know the limits of bias......Page 46
Considering the Many Different Roads to Learning......Page 47
Discovering the five main approaches......Page 48
Delving into some different approaches......Page 50
Pondering the True Uses of Machine Learning......Page 54
Understanding machine learning benefits......Page 55
Discovering machine learning limits......Page 57
Chapter 3 Getting and Using Python......Page 59
Obtaining Your Copy of Anaconda......Page 60
Installing Anaconda on Linux......Page 61
Installing Anaconda on MacOS......Page 62
Installing Anaconda on Windows......Page 63
Using Jupyter Notebook......Page 68
Defining the code repository......Page 70
Getting and using datasets......Page 75
Understanding cells......Page 76
Adding documentation cells......Page 77
Using other cell types......Page 78
Understanding the Use of Indentation......Page 79
Adding Comments......Page 80
Understanding comments......Page 81
Using comments to leave yourself reminders......Page 82
Getting Help with the Python Language......Page 83
Using the Google Colaboratory......Page 84
Chapter 4 Leveraging a Deep Learning Framework......Page 87
Defining the differences......Page 88
Explaining the popularity of frameworks......Page 89
Defining the deep learning framework......Page 91
Choosing a particular framework......Page 92
Caffe2......Page 93
PyTorch......Page 94
MXNet......Page 95
Grasping why TensorFlow is so good......Page 96
Making TensorFlow easier by using TFLearn......Page 98
Using Keras as the best simplifier......Page 99
Getting your copy of TensorFlow and Keras......Page 100
Fixing the C++ build tools error in Windows......Page 102
Accessing your new environment in Notebook......Page 103
Part 2 Considering Deep Learning Basics......Page 105
Chapter 5 Reviewing Matrix Math and Optimization......Page 107
Working with data......Page 108
Creating and operating with a matrix......Page 109
Understanding Scalar, Vector, and Matrix Operations......Page 110
Creating a matrix......Page 111
Performing matrix multiplication......Page 113
Executing advanced matrix operations......Page 114
Extending analysis to tensors......Page 116
Using vectorization effectively......Page 118
Exploring cost functions......Page 119
Descending the error curve......Page 120
Learning the right direction......Page 121
Updating......Page 123
Chapter 6 Laying Linear Regression Foundations......Page 125
Working through simple linear regression......Page 126
Advancing to multiple linear regression......Page 127
Including gradient descent......Page 129
Seeing linear regression in action......Page 130
Modeling the responses......Page 131
Modeling the features......Page 132
Dealing with complex relations......Page 133
Specifying a binary response......Page 135
Transforming numeric estimates into probabilities......Page 136
Defining the outcome of incompatible features......Page 138
Solving overfitting using selection and regularization......Page 139
Understanding how SGD is different......Page 141
Chapter 7 Introducing Neural Networks......Page 145
Understanding perceptron functionality......Page 146
Touching the nonseparability limit......Page 148
Considering the neuron......Page 150
Pushing data with feed-forward......Page 152
Going even deeper into the rabbit hole......Page 154
Using backpropagation to adjust learning......Page 157
Opening the black box......Page 160
Chapter 8 Building a Basic Neural Network......Page 163
Understanding Neural Networks......Page 164
Defining the basic architecture......Page 165
Documenting the essential modules......Page 167
Solving a simple problem......Page 169
Choosing the right activation function......Page 172
Relying on a smart optimizer......Page 174
Setting a working learning rate......Page 175
Chapter 9 Moving to Deep Learning......Page 177
Considering the effects of structure......Page 178
Understanding Moore’s implications......Page 179
Considering what Moore’s Law changes......Page 180
Discovering the Benefits of Additional Data......Page 181
Considering data timeliness and quality......Page 182
Improving Processing Speed......Page 183
Making other investments......Page 184
Explaining Deep Learning Differences from Other Forms of AI......Page 185
Adding more layers......Page 186
Changing the activations......Page 188
Adding regularization by dropout......Page 189
Using online learning......Page 190
Learning end to end......Page 191
Chapter 10 Explaining Convolutional Neural Networks......Page 193
Understanding image basics......Page 194
Understanding convolutions......Page 197
Simplifying the use of pooling......Page 201
Describing the LeNet architecture......Page 202
Detecting Edges and Shapes from Images......Page 207
Visualizing convolutions......Page 208
Unveiling successful architectures......Page 210
Discussing transfer learning......Page 211
Chapter 11 Introducing Recurrent Neural Networks......Page 215
Modeling sequences using memory......Page 216
Recognizing and translating speech......Page 218
Placing the correct caption on pictures......Page 220
Explaining Long Short-Term Memory......Page 221
Defining memory differences......Page 222
Walking through the LSTM architecture......Page 223
Discovering interesting variants......Page 225
Getting the necessary attention......Page 226
Part 3 Interacting with Deep Learning......Page 229
Chapter 12 Performing Image Classification......Page 231
Using Image Classification Challenges......Page 232
Delving into ImageNet and MS COCO......Page 233
Learning the magic of data augmentation......Page 235
Distinguishing Traffic Signs......Page 237
Preparing image data......Page 238
Running a classification task......Page 242
Chapter 13 Learning Advanced CNNs......Page 247
Distinguishing Classification Tasks......Page 248
Classifying multiple objects......Page 249
Segmenting images......Page 251
Discovering how RetinaNet works......Page 253
Using the Keras-RetinaNet code......Page 255
Overcoming Adversarial Attacks on Deep Learning Applications......Page 259
Tricking pixels......Page 260
Hacking with stickers and other artifacts......Page 262
Chapter 14 Working on Language Processing......Page 265
Processing Language......Page 266
Defining understanding as tokenization......Page 267
Putting all the documents into a bag......Page 268
Understanding semantics by word embeddings......Page 271
Using AI for Sentiment Analysis......Page 275
Chapter 15 Generating Music and Visual Art......Page 283
Learning to Imitate Art and Life......Page 284
Transferring an artistic style......Page 285
Reducing the problem to statistics......Page 286
Defining a new piece based on a single artist......Page 288
Visualizing how neural networks dream......Page 290
Using a network to compose music......Page 291
Chapter 16 Building Generative Adversarial Networks......Page 293
Finding the key in the competition......Page 294
Achieving more realistic results......Page 296
Inventing realistic pictures of celebrities......Page 303
Enhancing details and image translation......Page 304
Chapter 17 Playing with Deep Reinforcement Learning......Page 307
Introducing reinforcement learning......Page 308
Simulating game environments......Page 310
Presenting Q-learning......Page 313
Explaining Alpha-Go......Page 316
Determining if you’re going to win......Page 317
Applying self-learning at scale......Page 319
Part 4 The Part of Tens......Page 321
Chapter 18 Ten Applications that Require Deep Learning......Page 323
Approximating Person Poses in Real Time......Page 324
Performing Real-Time Behavior Analysis......Page 325
Estimating Solar Savings Potential......Page 326
Beating People at Computer Games......Page 327
Predicting Demographics......Page 328
Creating Art from Real-World Pictures......Page 329
Forecasting Natural Catastrophes......Page 330
Compiling Math Expressions Using Theano......Page 331
Augmenting TensorFlow Using Keras......Page 332
Creating a MATLAB-Like Environment with Torch......Page 333
Performing Tasks Dynamically with PyTorch......Page 334
Accelerating Deep Learning Research Using CUDA......Page 335
Mining Data Using Neural Designer......Page 337
Training Algorithms Using Microsoft Cognitive Toolkit (CNTK)......Page 338
Exploiting Full GPU Capability Using MXNet......Page 339
Managing People......Page 341
Improving Medicine......Page 342
Providing Customer Support......Page 343
Seeing Data in New Ways......Page 344
Creating a Better Work Environment......Page 345
Designing Buildings......Page 347
Enhancing Safety......Page 348
Index......Page 349
EULA......Page 371