상세정보

CONTENTS
Preface = xiii
Part Ⅰ. The Fundamentals of Machine learning
 1. The Machine learning landscape = 3
  What Is Machine Learning? = 4
  Why Use Machine Learning? = 4
  Types of Machine Learning Systems = 7
  Main Challenges of Machine Learning = 22
  Testing and Validating = 29
  Exercises = 31
 2. End-to-End Machine learning Project = 33
  Working with Real Data = 33
  Look at the Big Picture = 35
  Get the Data = 40
  Discover and Visualize the Data to Gain Insights = 53
  Prepare the Data for Machine Learning Algorithms = 60
  Select and Train a Model = 69
  Fine-Tune Your Model = 73
  Launch, Monitor, and Maintain Your System = 78
  Try It Out! = 78
  Exercises = 79
 3. Classification = 81
  MNIST = 81
  Training a Binary Classifier = 84
  Performance Measures = 84
  Multiclass Classification = 95
  Error Analysis = 98
  Multilabel Classification = 102
  Multioutput Classification = 103
  Exercises = 104
 4. Training Models = 107
  Linear Regression = 108
  Gradient Descent = 113
  Polynomial Regression = 123
  Learning Curves = 125
  Regularized Linear Models = 129
  Logistic Regression = 136
  Exercises = 145
 5. Support Vector Machines = 147
  Linear SVM Classification = 147
  Nonlinear SVM Classification = 151
  SVM Regression = 156
  Under the Hood = 158
  Exercises = 167
 6. Decision Trees = 169
  Training and Visualizing a Decision Tree = 169
  Making Predictions = 171
  Estimating Class Probabilities = 173
  The CART Training Algorithm = 173
  Computational Complexity = 174
  Gini Impurity or Entropy? = 174
  Regularization Hyperparameters = 175
  Regression = 177
  Instability = 179
  Exercises = 180
 7. Ensemble learning and Random Forests = 183
  Voting Classifiers = 183
  Bagging and Pasting = 187
  Random Patches and Random Subspaces = 190
  Random Forests = 191
  Boosting = 193
  Stacking = 202
  Exercises = 204
 8. Dimensionality Reduction = 207
  The Curse of Dimensionality = 208
  Main Approaches for Dimensionality Reduction = 209
  PCA = 213
  Kernel PCA = 220
  LLE = 223
  Other Dimensionality Reduction Techniques = 225
  Exercises = 226
Part Ⅱ. Neural Networks and Deep Learning
 9. Up and Running with TensorFiow = 231
  Installation = 234
  Creating Your First Graph and Running It in a Session = 234
  Managing Graphs = 236
  Lifecycle of a Node Value = 237
  Linear Regression with TensorFlow = 237
  Implementing Gradient Descent = 239
  Feeding Data to the Training Algorithm = 241
  Saving and Restoring Models = 243
  Visualizing the Graph and Training Curves Using Tensor Board = 244
  Name Scopes = 247
  Modularity = 248
  Sharing Variables = 250
  Exercises = 253
 10. Introduction to Artificial Neural Networks = 255
  From Biological to Artificial Neurons = 256
  Training an MLP with TensorFlow''''s High-Level API = 266
  Training a DNN Using Plain Tensor Flow = 267
  Fine-Tuning Neural Network Hyperparameters = 272
 11. Training Deep Neural Nets = 277
  Vanishing／Exploding Gradients Problems = 277
  Reusing Pretrained Layers = 289
  Faster Optimizers = 297
  Avoiding Overfitting Through Regularization = 307
  Practical Guidelines = 314
  Exercises = 315
 12. Distributing TensorFlow Across Devices and Servers = 317
  Multiple Devices on a Single Machine = 318
  Multiple Devices Across Multiple Servers = 328
  Parallelizing Neural Networks on a TensorFlow Cluster = 346
  Exercises = 357
 13. Convolutional Neural Networks = 359
  The Architecture of the Visual Cortex = 360
  Convolutional Layer = 361
  Pooling Layer = 369
  CNN Architectures = 371
  Exercises = 382
 14. Recurrent Neural Networks = 385
  Recurrent Neurons = 386
  Basic RNNs in TensorFlow = 390
  Training RNNs = 395
  Deep RNNs = 403
  LSTM Cell = 407
  GRU Cell = 410
  Natural Language Processing = 412
  Exercises = 417
 15. Autoencoders = 419
  Efficient Data Representations = 420
  Performing PCA with an Undercomplete Linear Autoencoder = 421
  Stacked Autoencoders = 423
  Unsupervised Pretraining Using Stacked Autoencoders = 430
  Denoising Autoencoders = 432
  Sparse Autoencoders = 434
  Variational Autoencoders = 437
  Other Autoencoders = 441
  Exercises = 442
 16. Reinforcement Learning = 445
  Learning to Optimize Rewards = 446
  Policy Search = 448
  Introduction to OpenAI Gym = 449
  Neural Network Policies = 453
  Evaluating Actions : The Credit Assignment Problem = 455
  Policy Gradients = 456
  Markov Decision Processes = 461
  Temporal Difference Learning and Q-Learning = 465
  Learning to Play Ms. Pac-Man Using Deep Q-Learning = 469
  Exercises = 477
Thank You! = 478
A. Exercise Solutions = 479
B. Machine Learning Projext Checklist = 505
C. SVM Dual Problem = 511
D. Autodiff = 515
E. Other Popular ANN Architectures = 523
Index = 533