Practical machine learning : tackle the real-world complexities of modern machine learning with innovative and cutting-edge techniques

목차 (Table of Contents)

• CONTENTS
• Preface = xi
• Chapter 1 Introduction to Machine learning = 1
• Machine learning = 2
• Definition = 3
• Core Concepts and Terminology = 4
• What is learning? = 4
• Data and inconsistencies in Machine learning = 12
• Practical Machine learning examples = 14
• Types of learning problems = 16
• Performance measures = 23
• Is the solution good? = 24
• Some complementing fields of Machine learning = 29
• Data mining = 30
• Artificial intelligence(AI) = 30
• Statistical learning = 31
• Data science = 32
• Machine learning process lifecycle and solution architecture = 32
• Machine learning algorithms = 33
• Decision tree based algorithms = 34
• Bayesian method based algorithms = 35
• Kernel method based algorithms = 35
• Clustering methods = 35
• Artificial neural networks(ANN) = 35
• Dimensionality reduction = 36
• Ensemble methods = 36
• Instance based learning algorithms = 37
• Regression analysis based algorithms = 37
• Association rule based learning algorithms = 37
• Machine learning tools and frameworks = 38
• Summary = 39
• Chapter 2 Machine learning and Large-scale datasets = 41
• Big data and the context of large-scale Machine learning = 42
• Functional versus Structural - A methodological mismatch = 43
• Machine learning : Scalability and Performance = 50
• Model selection process = 53
• Potential issues in large-scale Machine learning = 53
• Algorithms and Concurrency = 54
• Developing concurrent algorithms = 55
• Technology and implementation options for scaling-up Machine learning = 56
• MapReduce programming paradigm = 56
• High Performance Computing(HPC) with Message Passing Interface(MPI) = 58
• Language Integrated Queries(LINQ) framework = 58
• Manipulating datasets with LINQ = 59
• Graphics Processing Unit(GPU) = 59
• Field Programmable Gate Array(FPGA) = 61
• Multicore or multiprocessor systems = 62
• Summary = 62
• Chapter 3 An Introduction to Hadoop's Architecture and Ecosystem = 65
• Introduction to Apache Hadoop = 66
• Evolution of Hadoop(the platform of choice) = 67
• Hadoop and its core elements = 68
• Machine learning solution architecture for big data(employing Hadoop) = 68
• The Data Source layer = 69
• The Ingestion layer = 70
• The Hadoop Storage layer = 73
• The Hadoop(Physical) Infrastructure layer - supporting appliance = 74
• Hadoop platform／Processing layer = 76
• The Analytics layer = 77
• The Consumption layer = 78
• MapReduce = 91
• Hadoop 2.x = 99
• Hadoop ecosystem components = 100
• Hadoop installation and setup = 104
• Hadoop distributions and vendors = 111
• Summary = 112
• Chapter 4 Machine Learning Tools, Libraries, and Frameworks = 113
• Machine learning tools - A landscape = 114
• Apache Mahout = 116
• How does Mahout work? = 116
• Installing and setting up Apache Mahout = 118
• Mahout Packages = 123
• Implementing vectors in Mahout = 124
• R = 125
• Installing and setting up R = 127
• Integrating R with Apache Hadoop = 129
• Julia = 138
• Installing and setting up Julia = 138
• Running the Julia code from the command line = 141
• Implementing in Julia(with examples) = 141
• Using variables and assignments = 141
• Benefits of adopting Julia = 146
• Integrating Julia and Hadoop = 146
• Python = 148
• Toolkit options in Python = 148
• Implementation of Python(using examples) = 149
• Apache Spark = 151
• Scala = 152
• Programming with Resilient Distributed Datasets(RDD) = 154
• Spring XD = 155
• Summary = 157
• Chapter 5 Decision Tree based learning = 159
• Decision trees = 160
• Terminology = 160
• Purpose and uses = 161
• Constructing a Decision tree = 162
• Specialized trees = 178
• Implementing Decision trees = 183
• Using Mahout = 184
• Using R = 184
• Using Spark = 184
• Using Python(scikit-learn) = 184
• Using Julia = 184
• Summary = 184
• Chapter 6 Instance and Kernel Methods Based Learning = 185
• Instance-based learning(IBL) = 186
• Nearest Neighbors = 188
• Implementing KNN = 196
• Kernel methods-based learning = 197
• Kernel functions = 197
• Support Vector Machines(SVM) = 198
• Implementing SVM = 204
• Summary = 204
• Chapter 7 Association Rules based learning = 205
• Association rules based learning = 206
• Association rule - a definition = 207
• Apriori algorithm = 212
• FP-growth algorithm = 218
• Apriori versus FP-growth = 222
• Implementing Apriori and FP-growth = 223
• Using Mahout = 223
• Using R = 223
• Using Spark = 223
• Using Python(Scikit-learn) = 223
• Using Julia = 223
• Summary = 224
• Chapter 8 Clustering based learning = 225
• Clustering-based learning = 226
• Types of clustering = 228
• Hierarchical clustering = 228
• Partitional clustering = 230
• The k-means clustering algorithm = 231
• Convergence or stopping criteria for the k-means clustering = 232
• Advantages of the k-means approach = 234
• Disadvantages of the k-means algorithm = 235
• Distance measures = 236
• Complexity measures = 237
• Implementing k-means clustering = 237
• Using Mahout = 237
• Using R = 237
• Using Spark = 237
• Using Python(scikit-learn) = 237
• Using Julia = 237
• Summary = 238
• Chapter 9 Bayesian learning = 239
• Bayesian learning = 240
• Statistician's thinking = 241
• Bayes' theorem = 257
• Naive Bayes classifier = 259
• Implementing Naive Bayes algorithm = 264
• Using Mahout = 264
• Using R = 264
• Using Spark = 264
• Using scikit-learn = 264
• Using Julia = 264
• Summary = 264
• Chapter 10 Regression based learning = 265
• Regression analysis = 267
• Revisiting statistics = 268
• Confounding = 281
• Effect modification = 283
• Regression methods = 284
• Simple regression or simple linear regression = 287
• Multiple regression = 294
• Polynomial(non-linear) regression = 296
• Generalized Linear Models(GLM) = 298
• Logistic regression(logit link) = 298
• Poisson regression = 301
• Implementing linear and logistic regression = 301
• Using Mahout = 302
• Using R = 302
• Using Spark = 302
• Using scikit-learn = 302
• Using Julia = 302
• Summary = 302
• Chapter 11 Deep learning = 303
• Background = 305
• The human brain = 306
• Neural networks = 310
• Backpropagation algorithm = 326
• Softmax regression technique = 331
• Deep learning taxonomy = 332
• Convolutional neural networks(CNN／ConvNets) = 333
• Recurrent Neural Networks(RNNs) = 336
• Restricted Boltzmann Machines(RBMs) = 337
• Deep Boltzmann Machines(DBMs) = 338
• Autoencoders = 339
• Implementing ANNs and Deep learning methods = 340
• Using Mahout = 340
• Using R = 340
• Using Spark = 340
• Using Python(Scikit-learn) = 341
• Using Julia = 341
• Summary = 341
• Chapter 12 Reinforcement learning = 343
• Reinforcement Learning(RL) = 344
• The context of Reinforcement Learning = 346
• Reinforcement Learning - key features = 359
• Reinforcement learning solution methods = 359
• Dynamic Programming(DP) = 359
• Monte Carlo methods = 361
• Temporal difference(TD) learning = 362
• Q-Learning - off-Policy TD = 363
• Actor-critic methods(on-policy) = 364
• R Learning(Off-policy) = 365
• Summary = 366
• Chapter 13 Ensemble learning = 367
• Ensemble learning methods = 369
• The wisdom of the crowd = 369
• Key use cases = 374
• Ensemble methods = 377
• Implementing ensemble methods = 392
• Using Mahout = 392
• Using R = 392
• Using Spark = 392
• Using Python(Scikit-learn) = 392
• Using Julia = 392
• Summary = 392
• Chapter 14 New generation data architectures for Machine learning = 393
• Evolution of data architectures = 394
• Emerging perspectives＆drivers for new age data architectures = 397
• Modern data architectures for Machine learning = 404
• Semantic data architecture = 404
• Multi-model database architecture／polyglot persistence = 411
• Lambda Architecture(LA) = 416
• Summary = 418
• Index = 419