Encyclopedia of Machine Learning

Cover......Page 1
front-matter......Page 2
1-Norm Distance......Page 28
Motivation and Background......Page 30
Abduction in Artificial Intelligence......Page 31
Abductive Concept Learning......Page 32
Abduction and Induction......Page 33
Recommended Reading......Page 35
Definition......Page 36
Related Problems......Page 37
Common Active Learning Strategies......Page 38
Statistical Active Learning......Page 39
A Detailed Example: Statistical Active Learning with LOESS......Page 40
Definition......Page 41
Learning from Labeled and Unlabeled Data......Page 42
Example: Linear Separators in R2......Page 43
Generic Results for Separable Data......Page 44
A Bayesian Model......Page 45
Adaboost......Page 46
Motivation and Background......Page 47
Off-Line Versus On-Line......Page 48
Cross References......Page 49
Motivation and Background......Page 50
How CLEARS Mechanisms Interact......Page 51
Complementary Computing in the Brain: Resonance and Reset......Page 52
Resonance Links Intentional and Attentional Information Processing to Learning......Page 54
Controlling the Content of Conscious Experiences: Exemplars and Prototypes......Page 55
From Winner-Take-All to Distributed Coding......Page 56
ARTMAP Search and Match Tracking in Fuzzy ARTMAP......Page 58
ART Geometry......Page 61
Recommended Reading......Page 62
Motivation and Background......Page 63
Definition......Page 64
The Ant Colony Optimization Probabilistic Model......Page 65
The Ant Colony Optimization Pheromone Update......Page 66
Definition......Page 67
Definition......Page 68
Structure of the Learning System......Page 69
Supervised Immune-Inspired Learning......Page 70
Unsupervised Immune-Inspired Learning......Page 71
Synonyms......Page 72
Motivation and Background......Page 73
Modeling Learning......Page 74
Applications......Page 75
Definition......Page 76
Motivation and Background......Page 77
PAC Associative Reinforcement Learning......Page 78
Motivation and Background......Page 79
Recommended Reading......Page 80
Motivation and Background......Page 81
Typical Hardware Setup......Page 82
Modeling......Page 83
Differential Dynamic Programming......Page 85
Apprenticeship Learning and Inverse RL......Page 86
Conclusion......Page 88
Recommended Reading......Page 89
Classification with AODE......Page 90
Motivation and Background......Page 91
Model-Based Learning......Page 92
Scaling Average-Reward Reinforcement Learning......Page 93
Convergence Analysis......Page 94
Recommended Reading......Page 95
Gradient Descent......Page 96
Implementation......Page 97
Curve Fitting with BP......Page 98
Shortcomings of BP......Page 99
Bandit Problem with Side Observations......Page 100
Discussion......Page 101
Motivation and Background......Page 102
Basic Theory......Page 103
Justifications......Page 104
Bayesian Computation......Page 105
Recommended Reading......Page 107
Definition......Page 108
Examples......Page 109
Exchangeability......Page 111
Model Representations......Page 112
Consistency and Convergence Rates......Page 113
Examples......Page 114
General-Purpose Software Package......Page 115
Recommended Reading......Page 116
Structure of Learning Approach......Page 117
Optimal Value Function Parameterization......Page 118
Recommended Reading......Page 119
Definition......Page 120
Learning Direct (Situation–Action) Controllers......Page 121
Learning Indirect (Goal-Directed) Controllers......Page 122
Recommended Reading......Page 123
Bias......Page 124
DLAB......Page 125
FLIPPER\'s Bias Specification Language......Page 126
Definition......Page 127
Motivation and Background......Page 128
Monte Carlo Estimation of Integrals Using Importance Sampling......Page 129
Monte Carlo Optimization......Page 130
Parametric Machine Learning......Page 132
Solution Methodology......Page 133
Test Problems......Page 134
Application of PL Techniques......Page 135
Bias-Variance Trade-offs......Page 137
Motivation and Background......Page 138
The Hebb Rule......Page 139
Functional Consequences of Hebbian Learning......Page 140
Introduction......Page 141
Gene Expression Microarrays......Page 142
Machine Learning for Microarrays......Page 143
Single Nucleotide Polymorphisms......Page 145
Mass Spectrometry and Proteomics......Page 148
Protein Structures......Page 150
Related Data Types......Page 151
High-Throughput Screening Data for Drug Design......Page 152
Electronic Medical Records (EMR) and Personalized Medicine......Page 153
Conclusion......Page 157
Recommended Reading......Page 158
Definition......Page 159
The stochastic Dynamics of a Boltzmann Machine......Page 160
Different Types of Boltzmann Machine......Page 161
Learning Deep Networks by Composing Restricted Boltzmann Machines......Page 162
Boosting......Page 163
Breakeven Point......Page 164
Motivation and Background......Page 166
The Algorithm......Page 167
Recurrent Cascade-Correlation (RCC)......Page 169
CC......Page 170
KBCC......Page 172
Recommended Reading......Page 173
Definition......Page 174
Knowledge Containers......Page 175
Retrieval......Page 176
Reuse and Revision......Page 178
Applications......Page 179
Recommended Reading......Page 180
Motivation and Background......Page 181
Generic Data Clustering System......Page 182
Overlap-Based Similarity Measures......Page 183
Information-Theoretic Clustering Criteria......Page 184
Recommended Reading......Page 185
Motivation and Background......Page 186
Languages and Assumptions for Causal Inference......Page 187
Calculating Distributions under Interventions......Page 188
Learning Causal Structure......Page 190
Recommended Reading......Page 192
Definition......Page 193
Motivation and Background......Page 194
Motivation and Background......Page 195
Structure of the Learning System......Page 196
Recommended Reading......Page 197
Classification Tree......Page 198
Motivation and Background......Page 199
Structure of the Learning System......Page 200
Credit Assignment......Page 201
Rule Discovery Component......Page 202
Pittsburgh Classifier Systems......Page 203
Recommended Reading......Page 204
Clause......Page 205
Cluster Ensembles......Page 206
Basic Concepts......Page 207
Micro Clustering......Page 208
Monitoring the Evolution of the Cluster Structure......Page 209
Coevolution......Page 210
Multiple Versus Single Population Approaches......Page 211
Competition and Cooperation......Page 212
Evaluation......Page 213
Pathologies and Remedies......Page 214
Recommended Reading......Page 215
Motivation and Background......Page 216
Iterative Collective Classification with Neighborhood Labels......Page 217
Collective Classification with Graphical Models......Page 218
Cross References......Page 219
Community Detection......Page 220
Motivation and Background......Page 221
Adaptive System Environment and Regularities......Page 222
Application: Learning......Page 223
Data and Time Complexity......Page 225
Complexity of Final Hypothesis......Page 226
Learning Using Oracles......Page 227
Definition......Page 228
Definition......Page 229
Identifying Context Change......Page 230
Recent Advances......Page 231
Definition......Page 232
Background......Page 233
Concept Learning and Noise......Page 234
Recommended Reading......Page 235
Conjunctive Normal Form......Page 236
Detail......Page 237
Multi-Task or Context Sensitive Learning......Page 238
Special Cases of Inductive Logic Programming......Page 239
Behavioral Cloning......Page 241
Learning Geometric Clustering......Page 242
Recommended Reading......Page 243
Definition......Page 246
Structure of the Learning System......Page 247
Definition......Page 248
Constraints......Page 249
Borders......Page 250
Algorithms......Page 251
Recommended Reading......Page 252
Co-Reference Resolution......Page 253
Theory......Page 254
Applications......Page 256
Recommended Reading......Page 257
Motivation and Background......Page 258
Theory......Page 259
Structure of Learning System......Page 260
Cost-Sensitive Meta-Learning......Page 261
Motivation and Background......Page 262
Parameter Estimation......Page 263
Principal Component Analysis......Page 264
Definition......Page 265
Structural Credit Assignment......Page 266
Temporal Credit Assignment......Page 267
Recommended Reading......Page 268
Cross-Language QuestionAnswering......Page 269
Translation-Based Approaches......Page 270
Latent Semantic Approaches......Page 272
Kernel Canonical Correlation Analysis......Page 273
Cross-Language Information Retrieval (CLIR)......Page 274
Cross-Language Categorization (CLCat) and Clustering (CLCLu)......Page 275
Definition......Page 276
History......Page 277
Architecture......Page 279
Knowledge......Page 280
Learning......Page 282
Recommended Reading......Page 283
Background......Page 284
Recommended Reading......Page 285
Sourcing, Selecting, and Auditing Appropriate Data......Page 286
Data Preprocessing......Page 287
Definition......Page 288
Definition......Page 289
Representation......Page 290
Attribute Selection......Page 291
Recommended Reading......Page 293
Motivation and Background......Page 294
Deep Belief Nets with Other Types of Variable......Page 295
Deep Belief Networks......Page 296
Definition......Page 297
Structure of Learning System......Page 298
Recommended Reading......Page 300
Motivation and Background......Page 301
Dimensionality Reduction for Time-Series Data......Page 303
Dimensionality Reduction and Lower-Bounding......Page 304
Dimensionality Reduction on Text via Feature Selection......Page 306
Theory......Page 307
Dirichlet Process......Page 308
Predictive Distribution and the Blackwell–MacQueen Urn Scheme......Page 309
Clustering, Partitions, and the Chinese Restaurant Process......Page 310
Stick-Breaking Construction......Page 311
Dirichlet Process Mixture Models......Page 312
Further Reading......Page 313
Taxonomy......Page 314
Cross References......Page 315
Definition......Page 316
Data Representation......Page 317
Evaluation Measures......Page 318
Recommended Reading......Page 319
Structure of Learning System......Page 320
Partitional Document Clustering......Page 321
Evaluation of Document Clustering......Page 323
Recommended Reading......Page 324
Definition......Page 325
The Finite Horizon Setting......Page 326
Backward Induction Algorithm......Page 328
The Infinite Horizon Setting......Page 329
Solving the Infinite Horizon Discounted MDP......Page 330
Policy Iteration......Page 331
Policy Iteration......Page 332
Continuous Time Models......Page 333
Approximate Dynamic Programming......Page 334
Dynamic Systems......Page 335
Efficient Exploration in Markov Decision Processes......Page 336
Variations on MDP Learning......Page 337
EM Clustering......Page 338
Definition......Page 339
Methods for Combining a Set of Models......Page 340
Bagging......Page 341
Adaboost......Page 342
Mixtures of Experts......Page 343
Regression Error with a Linear Combination Rule......Page 344
Classification Error with a Linear Combination Rule......Page 345
Conclusions & Current Directions in the Field......Page 346
Definition......Page 347
Motivation and Background......Page 348
Theory/Solution......Page 349
Attribute-Based Entity Resolution......Page 350
Probabilistic Models for Relational Entity Resolution......Page 351
Recommended Reading......Page 352
Definition......Page 353
Definition......Page 354
Approaches and Methods......Page 355
Types of Equations......Page 356
Error......Page 357
Evaluation Data......Page 358
Definition......Page 359
Evolving Clusters and Evolving Clustering Algorithms......Page 360
Encodings and Operators for Evolutionary Clustering......Page 362
Evolutionary Multiobjective Clustering......Page 363
Definition......Page 364
Rationality and Learning......Page 365
Game Theory......Page 366
Agent-Based Models......Page 368
Evolutionary Computation in Finance......Page 369
Motivation and Background......Page 371
Financial Forecasting......Page 372
Portfolio Optimization......Page 373
Financial Markets......Page 374
Option Pricing......Page 375
Recommended Reading......Page 376
Applications......Page 378
Advertisement......Page 379
Definition......Page 380
Structure of Learning System......Page 381
Evolutionary Feature Selection......Page 382
Recommended Reading......Page 383
Motivation and Background......Page 384
Structure of the Learning System......Page 385
Optimization and Learning of the Fuzzy Rule Base......Page 386
Optimization and Learning of the Complete Knowledge Base......Page 387
Final Remarks......Page 388
Motivation and Background......Page 389
Genetic Programming......Page 390
Evolving Game-Playing Strategies......Page 391
Terminal and Function Sets......Page 393
Fitness Measure......Page 394
Chess (endgames)......Page 395
Motivation and Background......Page 396
Accuracy on Sample Data......Page 397
Encoding and Variation Operators......Page 398
Evolutionary Robotics......Page 399
Motivation and Background......Page 400
Structure of the Learning System......Page 401
Fitness Evaluation......Page 402
Applications......Page 403
Future Directions......Page 407
Evolving Neural Networks......Page 408
Synonyms......Page 409
Bayesian Machine Learning......Page 410
Expectation Propagation......Page 411
Convergence Issues......Page 412
Applications......Page 413
Experience Curve......Page 414
Motivation and Background......Page 415
Explanations and Their Generalization......Page 416
Evaluation and Hypothesis Selection......Page 417
Explanation-Based Learning for Planning......Page 418
Dimensions of Variation......Page 419
Learning from Success: Explanation-Based Generalization......Page 420
EBL from Incomplete Domain Theories......Page 421
Current Status......Page 422
Recommended Reading......Page 423
Definition......Page 424
Word-Based Features......Page 425
Linear Algebra Methods......Page 427
Recommended Reading......Page 428
Motivation and Background......Page 429
Categories of Feature Selection......Page 430
Evaluation of Feature Selection......Page 431
Feature Selection Development and Applications......Page 432
Definition......Page 433
Structure of Learning System......Page 434
Recommended Reading......Page 436
Motivation and Background......Page 437
Semantics......Page 438
Proofs......Page 439
Programming in Logic......Page 440
Definition......Page 442
Foil......Page 443
Definition......Page 444
Structure of Problem......Page 445
Theory/solutions......Page 446
Condensed Representations: Closed Sets andNonderivable Sets......Page 447
Recommended Reading......Page 449
Recommended Reading......Page 450
Motivation and Background......Page 452
Entropy and Kullback–Leibler Divergence......Page 453
3-bold0mu mumu  Rule......Page 454
Definition......Page 455
Gaussian Process......Page 456
Covariance Functions......Page 457
Predictive Distribution:......Page 459
Likelihood Function and Posterior Distribution:......Page 460
Predictive Distribution:......Page 461
Practical Issues......Page 462
Sparse Approximation......Page 463
Current and Future Directions......Page 464
Recommended Reading......Page 465
Definition......Page 466
Markov Decision Processes......Page 467
Structure of Learning System......Page 468
Gaussian Process Temporal Difference Learning......Page 470
General MRPs......Page 471
Applications......Page 472
Recommended Reading......Page 473
Motivation and Background......Page 474
Details......Page 475
Recommended Readings......Page 480
Definition......Page 481
Definition......Page 482
Genetic Operators......Page 483
Gibbs Sampling......Page 484
Recommended Reading......Page 485
Motivation and Background......Page 486
Graph Clustering as Minimum Cut......Page 487
Graph Clustering with k-Means......Page 488
Graph Clustering with the Spectral Method......Page 489
Graph Clustering as Quasi-Clique Detection......Page 490
Graph Clustering as Dense Subgraph Determination......Page 491
Clustering Graphs as Objects......Page 492
Conclusions and Future Research......Page 493
Approaches for Kernels between Graphs......Page 494
Approaches for Kernels on a Graph......Page 495
Structure of Learning System......Page 496
Applications......Page 497
Definition......Page 498
Directed Graphical Models......Page 499
Undirected Graphical Models......Page 500
Characterization of Directed and Undirected Graphical Models......Page 501
Inference Algorithms in Graphical Models......Page 502
The Junction-Tree Algorithm......Page 503
Approximate Inference......Page 504
Recommended Reading......Page 505
Isomorphism......Page 506
Properties of Graphs......Page 507
Applications......Page 508
Greedy Search......Page 509
Motivation and Background......Page 510
Structure of Learning System......Page 511
Graph-Based Supervised Learning......Page 512
Programs and Data......Page 513
Applications......Page 514
Recommended Reading......Page 515
Theory Solution......Page 516
Clustering Techniques......Page 517
Issues......Page 518
Growth Function......Page 519
Structure of the Learning System......Page 520
Recommended Reading......Page 521
Motivation and Background......Page 522
Structure of HRL......Page 523
Semi-Markov Decision Problem Formalism......Page 524
Hierarchies of Abstract Machines (HAMs)......Page 525
MAXQ......Page 526
Recommended Reading......Page 528
Motivation and Background......Page 529
Logic......Page 530
Knowledge Representation......Page 531
Cross References......Page 532
Definition......Page 533
Definition......Page 534
Graphical Models......Page 535
Clustering......Page 536
First-Order Logic Versus Propositional Languages......Page 537
Hypothesis Space......Page 538
Theory......Page 539
Definition......Page 540
Definition......Page 542
Theory......Page 543
Recommended Reading......Page 545
Induction and Probabilistic Inference......Page 546
Popper......Page 547
Cross References......Page 548
Query Language......Page 549
Inductive Inference......Page 550
Explanatory Learning......Page 551
Beyond Explanatory Learning......Page 552
Monotonicity......Page 553
Indexed Families......Page 554
Inductive Inference......Page 555
Motivation......Page 556
Theory......Page 557
A Methodology......Page 558
Application......Page 559
Current Trends and Challenges......Page 560
Recommended Reading......Page 561
Definition......Page 562
Motivation and Background......Page 564
The Evidence and the Oracle......Page 565
Program Schemas......Page 566
Predicate Invention......Page 567
Programs and Data......Page 568
Future Directions......Page 570
Inductive Synthesis......Page 571
Neural Networks......Page 572
Theoretical Work......Page 573
Future Directions......Page 574
Cross References......Page 575
Motivation and Background......Page 576
Structure of Learning System......Page 577
Examples of IBRL Algorithms......Page 578
Problems and Drawbacks......Page 579
Definition......Page 580
Motivation and Background......Page 581
Characterization of the Inverse RL Solution Set......Page 582
Statistical Efficiency......Page 583
Recommended Reading......Page 584
Iterative Classification......Page 585
Junk Email Filtering......Page 586
The Stochastic k-Armed Bandit Problem......Page 588
Recommended Reading......Page 591
Recommended Reading......Page 592
Theory......Page 593
Kernel Function Classes......Page 594
Unsupervised Learning......Page 595
Recommended Reading......Page 596
Kohonen Maps......Page 597
The Non-stochastic k-Armed Bandit Problem......Page 589
K-Means Clustering......Page 590
Definition......Page 598
Representation......Page 599
Version Spaces and Subsumption......Page 601
Recommended Reading......Page 603
Motivation and Background......Page 604
General Machine Learning......Page 605
Definition......Page 607
Main Tasks and Solution Approaches......Page 608
Recommended Reading......Page 610
Motivation and Background......Page 611
Statistical Equivalence......Page 612
Constraint Learners......Page 613
Search and Complexity......Page 614
Knowledge Engineering with Bayesian Networks......Page 615
Recommended Reading......Page 616
Definition......Page 617
Proteins......Page 618
Genes......Page 619
Programs and Data......Page 620
Definition......Page 621
Motivation and Background......Page 622
Least-Squares Fixed-Point Approximation......Page 623
Least-Squares Temporal Difference Learning......Page 624
Least-Squares Policy Evaluation......Page 625
Least-Squares Policy Iteration......Page 626
Definition......Page 627
Motivation and Background......Page 628
Fisher\'s Discriminant for Two-Category Problem......Page 629
Motivation and Background......Page 630
Geometrical Interpretation of Least Squares Method......Page 631
Ridge regression......Page 632
Definition......Page 633
Data Representation......Page 634
Recommended Reading......Page 635
Theory/Solution......Page 636
Node Attribute-Based Approaches......Page 637
Related Problems......Page 638
Recommended Reading......Page 639
Definition......Page 640
Motivation and Background......Page 641
Background......Page 642
Locally Weighted Projection Regression (LWPR)......Page 643
A Full Bayesian Treatment of Locally Weighted Regression......Page 644
Learning Internal Models with LWPR......Page 646
Learning Paired Inverse-Forward Models......Page 647
Learning Trajectory Optimizations......Page 648
Recommended Reading......Page 650
Learning from Entailment......Page 651
An Operational Perspective......Page 652
Propositional Subsumption......Page 653
-Subsumption......Page 654
Background Knowledge......Page 656
Recommended Reading......Page 657
Logit Model......Page 658
LWR......Page 659
Learning of Evaluation Functions......Page 660
Learning Search Control......Page 661
Player Modeling......Page 662
Recommended Reading......Page 663
Structure of Learning System......Page 664
Recommended Reading......Page 665
Definition......Page 666
The Metropolis Algorithm......Page 667
Recommended Reading......Page 668
Average Reward......Page 669
Bellman Error Minimization......Page 670
Representations......Page 671
Recommended Reading......Page 672
Structure of Learning System......Page 674
Recommended Reading......Page 673
Relationship to Maximum Likelihood......Page 675
Model Specification......Page 676
Search for Best Sequence......Page 677
Definition......Page 678
Mean Shift......Page 679
Levels of Measurement Scales......Page 680
Motivation......Page 681
Diversity of Representations......Page 682
Diagnosis and Medication......Page 683
Prognosis and Quality of Care Assessment......Page 685
Epidemiology and Outbreak Detection......Page 686
Recommended Reading......Page 687
Message......Page 688
Motivation and Background......Page 689
How the Subset of Algorithms Is Identified......Page 690
Acquisition of Metaknowledge......Page 691
Inductive Transfer......Page 692
Motivation and Background......Page 693
Optimal Yardstick......Page 694
Definition......Page 695
Motivation and Background......Page 696
Example with Binomial Distribution......Page 697
Applications......Page 698
Probabilistic Finite State Machines......Page 699
Future Directions......Page 700
Definition......Page 701
Strategies for Missing Value Processing......Page 702
Missing Value Processing Techniques in Various ML Paradigms......Page 705
Recommended Reading......Page 706
Definition......Page 707
Types of Component Distributions......Page 708
Recommended Reading......Page 709
Model Space......Page 710
Structure of Learning System......Page 711
Recommended Reading......Page 712
Generative Model......Page 713
Learning......Page 714
Model-Based Control......Page 716
Theory and Methods......Page 717
Cross References......Page 719
Cross References......Page 720
Background......Page 721
Problem Definition......Page 722
Definition......Page 723
Model-Free Approaches......Page 724
Some Typical Results......Page 725
Definition......Page 726
Algorithm......Page 727
Motivation and Background......Page 728
Structure of the Problem......Page 729
Multiple-Instance Classification......Page 730
Applications......Page 734
Recommended Reading......Page 736
Definition......Page 737
Must-Link Constraint......Page 738
Structure of Learning System......Page 740
Motivation and Background......Page 741
Negative Predictive Value......Page 742
Motivation and Background......Page 743
Basic methods......Page 744
Extensions......Page 745
Applications......Page 746
Definition......Page 747
Noise......Page 748
Formal Background......Page 749
Support Vector Machines......Page 750
Ensemble methods......Page 751
Evolutionary Regularization......Page 752
Ensemble Learning and Boosting......Page 753
Boosting and Large-Scale Learning......Page 754
AUC: Area Under the ROC Curve......Page 755
Recommended Reading......Page 756
Definition......Page 758
Definition......Page 759
Attribute-Value Learning......Page 760
Relational Learning......Page 761
Recommended Reading......Page 762
Definition......Page 763
Structure of Learning System......Page 764
TheWeighted Majority Algorithm......Page 765
Tracking the best expert and other structured experts.......Page 766
Prediction with limited feedback and the multiarmedbandit problem.......Page 767
Analysis of the perceptron algorithm.......Page 768
Recommended Reading......Page 769
Overall and Class-SensitiveFrequencies......Page 770
Overtraining......Page 771
Motivation and Background......Page 772
Remarks......Page 774
The Finite Case......Page 775
The Infinite Case......Page 776
Relations to Other Learning Models......Page 779
PAC-MDP Learning......Page 780
POMDP Model......Page 781
Policies......Page 782
Solution Algorithms......Page 784
Recommended Reading......Page 786
The Canonical Particle Swarm......Page 787
The Social–Psychological Metaphor......Page 788
Vmax and Convergence......Page 789
Generalizing the Notation......Page 790
Alternative Probability Distributions......Page 791
Recommended Reading......Page 792
PCFG......Page 793
Relational Learning......Page 794
Relational Kernels and MIL Problems......Page 796
The MI-SVM PT......Page 797
Propositional Regression......Page 798
Perspectives......Page 799
Piecewise Linear Models......Page 800
Gradient Descent in Policy Space......Page 801
Likelihood-Ratio Gradients......Page 802
Definition......Page 803
Motivation and Background......Page 804
Other Supervised Learning Methods......Page 805
Definition......Page 806
Cross References......Page 807
Definition......Page 808
Introduction......Page 809
The Process of Applying ML to SE......Page 810
Software size prediction......Page 811
Software Cost Prediction......Page 812
Software Reusability Prediction......Page 813
Other Applications......Page 814
Future Directions......Page 815
Definition......Page 816
Structure of the Learning System......Page 817
Learning from Label Preferences......Page 818
Learning Utility Functions......Page 819
Learning Preference Relations......Page 820
Recommended Reading......Page 821
Motivation and Background......Page 822
Protecting Centralized Data......Page 823
Protecting the Model (Centralized Data)......Page 824
Distributed Data......Page 825
Future Directions......Page 827
Recommended Reading......Page 828
Derivation Process......Page 829
Learning......Page 830
Application to Bioinformatics......Page 831
Programming by Example......Page 832
Motivation and Background......Page 833
Theory......Page 834
Algorithms......Page 835
Applications......Page 836
Coresets......Page 837
Recommended Reading......Page 838
Motivation and Background......Page 839
Functional Relationship (Many-To-One, One-To-One)......Page 840
CommonMistakes and Key Rules to Avoid them......Page 841
Further Relationships......Page 842
Future Directions......Page 843
Cross References......Page 844
Recommended Reading......Page 846
Detail......Page 847
Recommended Reading......Page 849
Motivation and Background......Page 850
Structure of the Network/Learning System......Page 851
Regularization and Generalizations......Page 852
Random Decision Forests......Page 854
Ratio Scale......Page 855
Motivation and Background......Page 856
Collaborative Filtering......Page 857
Neighborhood-based Collaborative Filtering......Page 858
Model-based Collaborative Filtering......Page 859
Hybrid Approaches......Page 861
Evaluation Metrics......Page 862
Challenges and Limitations......Page 863
Recommended Reading......Page 864
Motivation and Background......Page 865
Fitting......Page 866
Bias-Variance Dilemma......Page 867
Other Variants of Regression......Page 868
Motivation and Background......Page 869
Learning a Regression Tree......Page 870
Pruning Regression Trees......Page 871
Definition......Page 872
An Illustrative Example: Ridge Regression......Page 873
Examples of Regularization......Page 874
Applications......Page 875
Reinforcement Learning......Page 876
Cross References......Page 877
Learning from Examples with External Relationships......Page 878
Inductive Logic Programming......Page 879
Learning from Graphs......Page 880
Multi-relational Data Mining......Page 881
Statistical Relational Learning/Probabilistic Logic Learning......Page 882
Recommended Reading......Page 883
Motivation and Background......Page 884
Structure of the Learning System......Page 885
Added Benefits of Relational Reinforcement Learning......Page 886
Non-parametric Policy Gradients......Page 887
Symbolic Dynamic Programming......Page 888
Relevance Feedback......Page 889
Definition......Page 890
Potential-Based Shaping......Page 891
Robot Skill Learning Problems......Page 892
Imitation and Apprenticeship Learning......Page 893
Robot Reinforcement Learning......Page 894
Recommended Reading......Page 895
Solutions......Page 896
The AUC Statistic......Page 898
Obtaining Calibrated Estimates of the Class Posterior......Page 899
Recommended Reading......Page 901
The Covering Algorithm......Page 902
Finding the Best Rule......Page 903
Overfitting Avoidance......Page 904
Well-known Rule Learning Algorithms......Page 905
Recommended Reading......Page 906
Search Bias......Page 908
Structure of the Learning System......Page 909
Retrieval Methods......Page 910
Query Classification......Page 911
Cross References......Page 912
Motivation and Background......Page 913
Structure of Learning System......Page 914
Semantic Mapping......Page 915
Methods That Apply Naive Bayes to a Subset of Attributes......Page 916
Methods That Calibrate Naive Bayes\' Probability Estimates......Page 917
Selection Between Semi-Naive Bayesian Methods......Page 918
Definition......Page 919
Generative Models......Page 920
Graph-Based Models......Page 921
A PAC Bound for Semi-Supervised Learning......Page 922
Future Directions......Page 923
Definition......Page 924
Generative Models......Page 925
Multiview Approaches......Page 926
Approaches that Exploit Background Knowledge......Page 927
Definition......Page 928
Definition......Page 929
Classes of Similarity Functions......Page 930
Cross References......Page 932
Spam Detection......Page 933
Motivation and Background......Page 934
Dimensions of Speedup Learning......Page 935
Examples of Intra-Problem Speedup Learning......Page 936
Examples of Inter-Problem Speedup Learning......Page 937
Speedup Learning For Planning......Page 938
Definition......Page 939
Modeling......Page 940
Estimation......Page 941
Programs and Data......Page 942
Motivation and Background......Page 943
Statistical Relational Languages......Page 944
Case Study: Markov Logic Networks......Page 945
Case Study: ProbLog......Page 946
Learning......Page 947
Structure Learning......Page 948
Future Directions......Page 949
Recommended Reading......Page 950
Motivation and Background......Page 952
Learning Monomials......Page 953
Learning Pattern Languages......Page 954
Stream Mining......Page 955
Definition......Page 956
Motivation and Background......Page 957
Structured Versus Unstructured Induction......Page 958
Recommended Reading......Page 959
Structure of the Learning System......Page 960
Quality of Uniformly Random Sampling:......Page 961
Property Testing of the Quality of Clustering:......Page 962
Applications......Page 963
Recommended Reading......Page 964
Motivation and Background......Page 965
Structure of the Learning System......Page 966
Cross References......Page 967
Motivation and Background......Page 968
Optimal Hyperplane for Linearly Separable Examples......Page 969
Dual Forms and Kernelization......Page 970
Optimization Techniques and Toolkits......Page 971
Further Reading......Page 972
Definition......Page 973
Background: Markov Decision Processes (MDPs)......Page 974
First-Order Markov Decision Processes......Page 977
Symbolic Dynamic Programming......Page 978
Applications......Page 979
Recommended Reading......Page 980
Synaptic E.Cacy......Page 981
Recommended Reading......Page 982
Formal Definitions......Page 983
Eligibility Traces and TD(bold0mu mumu )......Page 984
Actor-Critic Control Systems......Page 985
Other Value Functions......Page 986
Related Differencing Systems......Page 987
Recommended Reading......Page 988
Definition......Page 989
Motivation and Background......Page 990
Structure of Learning Systems......Page 992
Learning with Genetic Programming......Page 993
Recommended Reading......Page 994
Motivation and Background......Page 995
Tasks......Page 996
Solution Approaches......Page 997
Recommended Reading......Page 998
Data Acquisition......Page 999
Feature Extraction and Selection......Page 1000
Learning Algorithms......Page 1001
User-specific Versus User-independent Spam Detection......Page 1002
Misclassification Costs and Filter Evaluation......Page 1003
Cross References......Page 1004
Motivation and Background......Page 1005
Structure of Learning System......Page 1006
Motivation and Background......Page 1007
Structure of Learning System......Page 1008
IN-SPIRE......Page 1011
Starlight......Page 1012
TF–IDF......Page 1013
Motivation and Background......Page 1014
Definition......Page 1015
Training Examples......Page 1016
Classification with TAN......Page 1017
Motivation and Background......Page 1018
Structure of Problem......Page 1019
Theory/Solution......Page 1020
Encoding and Enumerating Trees......Page 1021
Counting Trees......Page 1022
Applications......Page 1024
Recommended Reading......Page 1025
Typical Complexity of Learning......Page 1026
Learning by enumeration......Page 1028
(Universal) monotone Turing machines......Page 1029
Bayes......Page 1030
Representations......Page 1031
Universal Sequential Decisions......Page 1032
Universal Reinforcement Learning......Page 1033
Discussion and Future Directions......Page 1034
Unstable Learner......Page 1035
Utility Problem......Page 1036
Markov Decision Processes......Page 1038
Bellman Equations......Page 1039
Significance of Value Functions......Page 1040
Value Function Approximation......Page 1041
Approximation Architectures......Page 1042
Learning......Page 1044
Inverted Pendulum......Page 1045
Mountain Car......Page 1046
Recommended Reading......Page 1047
Remarks......Page 1048
Examples......Page 1049
Applications......Page 1050
Definition......Page 1051
Recommended Reading......Page 1052
Definition......Page 1054
Methods......Page 1055
Machine Learning......Page 1056
Word Sense Discrimination......Page 1057
Zero-One Loss......Page 1058