Data Mining: Practical Machine Learning Tools and Techniques, Second Edition

A

activation function, 234

acuity, 258

AdaBoost, 328

AdaBoost.M1, 321, 416

Add, 395

AddCluster, 396, 397

AddExpression, 397

additive logistic regression, 327–328

additive regression, 325–327

AdditiveRegression, 416

AddNoise, 400

AD (all-dimensions) tree, 280–283

ADTree, 408

advanced methods.Seeimplementation—

real-world schemes

adversarial data mining, 356–358

aggregation, appropriate degree in data

warehousing, 53

Akaike Information Criterion (AIC), 277

Alberta Ingenuity Centre for Machine

Learning, 38

algorithms

additive logistic regression, 327

advanced methods, 187–283.See also

implementation—real-world schemes

association rule mining, 112–119

bagging, 319

basic methods, 83–142.See alsoalgorithms-

basic methods

Bayesian network learning, 277–283

clustering, 136–139

clustering in Weka, 418–419

covering, 105–112

decision tree induction, 97–105

divide-and-conquer, 107

EM, 265–266

expanding examples into partial tree, 208

filtering in Weka, 393–403.See alsofiltering

algorithms

incremental, 346

instance-based learning, 128–136

learning in Weka, 403–414.See alsolearning

algorithms

linear models, 119–128

metalearning in Weka, 414–418

1R method, 84–88

perceptron learning rule, 124

RIPPER rule learner, 206

rule formation-incremental reduced-error

pruning, 205

separate-and-conquer, 112

statistical modeling, 88–97

stochastic, 348

Winnow, 127

See alsoindividual subject headings.

all-dimensions (AD) tree, 280–283

alternating decision tree, 329, 330, 343

Analyzepanel, 443–445

analyzing purchasing patterns, 27

ancestor-of, 48

anomalies, 314–315

Index

505

P088407-INDEX.qxd 4/30/05 11:25 AM Page 505