Kecman V. — Learning and soft computing. Support vector machines, neural networks, and fuzzy logic models :: Электронная библиотека попечительского совета мехмата МГУ

Главная Ex Libris Книги Журналы Статьи Серии Каталог Wanted Загрузка ХудЛит Справка Поиск по индексам Поиск Форум

Авторизация

Поиск по указателям

Kecman V. — Learning and soft computing. Support vector machines, neural networks, and fuzzy logic models

Обсудите книгу на научном форуме

Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter

Название: Learning and soft computing. Support vector machines, neural networks, and fuzzy logic models

Автор: Kecman V.

Аннотация:

This textbook provides a thorough introduction to the field of learning from experimental data and soft computing. Support vector machines (SVM) and neural networks (NN) are the mathematical structures, or models, that underlie learning, while fuzzy logic systems (FLS) enable us to embed structured human knowledge into workable algorithms. The book assumes that it is not only useful, but necessary, to treat SVM, NN, and FLS as parts of a connected whole. Throughout, the theory and algorithms are illustrated by practical examples, as well as by problem sets and simulated experiments. This approach enables the reader to develop SVM, NN, and FLS in addition to understanding them. The book also presents three case studies: on NN-based control, financial timeseries analysis, and computer graphics. A solutions manual and all of the MATLAB programs needed for the simulated experiments are available.

Язык:

Рубрика: Computer science/AI, knowledge/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Год издания: 2001

Количество страниц: 541

Добавлена в каталог: 16.05.2005

Операции: Положить на полку | Скопировать ссылку для форума | Скопировать ID

Предметный указатель

$\varepsilon$ -insensitivity zone      177
ABC adaptive backthrough control      429—449
ABC adaptive backthrough control, ABC of time-variant plant      440—443
ABC adaptive backthrough control, back propagation through a plant      427—428
Activation function      15—17 259 275—290
ADALINE      213
Additive noise      124
Animation      470—474
Approximating function      126
Approximation      29 34—41
Approximation error      134 136
Asymptotic consistency      131
Attribute      See membership function
Back propagation through a plant      427—428
Bayes decision criterion      71 78
Bayes risk      71 86
Bayesian classification      77—81
Best approximation      29
BFGS optimization method      488
Bias (offset, threshold) in NN      15 150 157 181 182 196 206 289
Bias-variance      40 136 268—274
Binary classification      71
Bipolar sigmoidal function      259
Canonical hyperplane      152
Classification      68 149 162 166
Classification, binary      71
Classification, dichotomization      91
Classifiers, parametric      92
Classifiers, template matching      101
Composition in FL      380—382
Computer graphics      463—480
Conjugate gradient method      430 489—494
Consistent estimators      275
Covariance matrix      93 334 341 529
Crafting sigmoidal AF (learning)      280—283
Cross-validation      40 137 269 272
Davidon — Fletcher — Powell method      487
Decision boundary      151
Decision regions      70 88
Defuzzification methods      393
Defuzzification methods, center-of-area      393
Defuzzification methods, center-of-gravity      393
Defuzzification methods, first-of-maxima      393
Defuzzification methods, middle-of-maxima      393
Degree of belonging      372 376
Delta signal, $\delta$ -signal      234 257
Design matrix      35
Dichotomization      91
Discriminant function      89
Discriminant function for normally distributed classes      93—95
Distal teacher      426 428
EBP error back propagation      255—266
Empirical risk minimization ERM      130
Epoch      6 208 230
Equality of NNs arid FLMs      396
Error correction learning      194 204 234 236
Error signal term (\breve{S} signal)      234 257
Error stopping function      292
Error surface      44—53 302 484
Estimation error      135
Evolutionary computing      496—504
Facial animation      473
FAM, fuzzy additive model      404—410
Financial time series      449—463
Fletcher — Powell method      487
Fletcher — Reeves CG method      492
Fourier series and NN      47
Fuzzy logic systems, composition      380—382
Fuzzy logic systems, defuzzification      391—394
Fuzzy logic systems, defuzzification, center-of-area      393
Fuzzy logic systems, defuzzification, center-of-gravity      393
Fuzzy logic systems, defuzzification, first-of-maxima      393
Fuzzy logic systems, defuzzification, middle-of-maxima      393
Fuzzy logic systems, degree of belonging      372 376
Fuzzy logic systems, design steps for FL models      405
Fuzzy logic systems, fuzzification      385 391
Fuzzy logic systems, fuzzy additive models (FAM)      386 404—410
Fuzzy logic systems, IF-THEN rules      378
Fuzzy logic systems, implication      383—385
Fuzzy logic systems, inference      382—391
Fuzzy logic systems, membership function      21—24 367—371
Fuzzy logic systems, normal f. sets      368
Fuzzy logic systems, not-normal f. sets      368
Fuzzy logic systems, possibility degree      376
Fuzzy logic systems, relational matrix      376—382
Fuzzy logic systems, relations      374
Fuzzy logic systems, rule explosion      408
Fuzzy logic systems, S-norm      373
Fuzzy logic systems, set operations      371
Fuzzy logic systems, sets      367
Fuzzy logic systems, surface of knowledge      394—396
Fuzzy logic systems, T-norm      373
Fuzzy logic systems, trapezoidal membership function      371
Fuzzy logic systems, triangular membership function      371
Gauss — Newton method      495
Generalization error      134
Generalization of NNs and SVMs      40 269
Generalized delta ( $\delta$ ) rule      260 263
Generalized least squares      495
Genetic algorithms      496—504
Geometry of learning      277—288
Gradient method      49 54—60 230—237 301—302 518
Gramm — Schmidt orthogonalization      348
Graphics by RBF networks      463—480
Green's function      320
Growth function      144
Hessian matrix      57 229 296 301 485 495
Human animation      470—474
Hypothesis space      134
Ideal control      421
IF-THEN rules      378
Ill-posed problem      202 314
Indicator function      138 150
Insensitivity or s zone      177

Interpolation      34—41
Jacobian      428—430
Karash — Kuhn — Tucker condition      156
kernels      170
Key learning theorem      131
Kolmogorov theorem      13
Lagrangian, dual      156 163 172 180
Lagrangian, primal      156 163 172 180
Learning      61
Learning fuzzy rules (LFR)      396
Learning machine      126
Learning, 1. by subset selection      146 334 353
Learning, 1. of linear neuron weights (5 methods)      225
Learning, 1. rate $\eta$       194 296
Learning, momentum term      296—301
Learning, moving center learning      337
Levenberg — Marquardt method      495
Likelihood ratio      78
Linear dynamic system      223
Linear neuron      213
Linear programming (LP)      353—358
Linear separability      202
LMS learning algorithm      234
Logistic (unipolar sigmoidal) function      259
Loss function      81 84 126
Lp norms      28—31 512
Mahalanobis distance      94 100
MAP maximal-a-posteriori decision criterion      71
Margin      153
Matrix-inversion lemma      237 239
Maximal margin classifier      149
Maximal-a-priori decision criterion      71
Membership function      21—24 367—371
Mercer kernels      170
MLP multilayer perceptron      15—18 26 255
Momentum term      296—301
Morphing      466—470
Multiclass classification      80
NARMAX model      422 433 451
Nested set of functions      114
Newton — Raphson method      229 301—302 485
NNs based control      421
NNs based control, ABC of time-variant plant      440—443
NNs based control, adaptive backthrough control ABC      429—449
NNs based control, backpropagation through a plant      427—428
NNs based control, dead-beat controller      433
NNs based control, direct inverse modeling      423
NNs based control, distal teacher      426 428
NNs based control, errors, definition of      431
NNs based control, errors, definition of, controller error      431
NNs based control, errors, definition of, performance error      431
NNs based control, errors, definition of, predicted performance error      431
NNs based control, errors, definition of, prediction error      431
NNs based control, general learning architecture      423
NNs based control, ideal linear controller      421
NNs based control, IMC internal model control      431
NNs based control, indirect learning architecture      425
NNs based control, Jacobian of the plant      428—430
NNs based control, parallel model      422
NNs based control, series-parallel model      422
NNs based control, specialized learning architecture      425
Noise influence on estimation      220 224
Nonradial BFs      337 339
Norm      28—31 512
Normal equation      228 344
OLS orthogonal least squares      343
Orthogonalization      350—352
Overfitting      41 269
Parametric classifier      92
Penalty parameter C      163
Perceptron      194
Perceptron, convergence of the p. learning rule      199
Perceptron, p. learning algorithms      204
Polak — Ribiere CG method      493
Possibility degree      376
Powell's quadratic approximation      58—61
Projection matrix      348
Quadratic programming      156—158 163—165 172—173 180—181
Quasi — Newton methods      486
Radial basis functions (RBFs) network      15—18 26 33—41 313—358 463 478
Regression      62—68 176 354—357 515
Regularization      314
Regularization parameter $\lambda$       137 320 329
Reproducing kernels      170
Ridge regression      137
Risk      85
RLS recursive-least-squares      237—241
Rule explosion      408
Second order optimization methods      483—496
Share market      450
Sigmoidal functions, bipolar s. f.      259
Sigmoidal functions, logistic (unipolar) function      259
Similarity between RBFs and FLMs      395—404
Soft margin      162
SRM, structural risk minimization      145 161
Stabilizer (in RBFs network)      320 329
Subset selection      146 334 353
Support vector      157
Support vector machines, SVMs      148
Support vector machines, SVMs, for classification      149 162 166
Support vector machines, SVMs, for regression      176
Surface of knowledge      394—396
System of linear equations      505
Underfitting      269
Uniform convergence      131
Universal approximation      36—37
Universe of discourse      367
Variable metric method      486
Variance      134—136
VC dimension      138
Vectors and matrices      510—514
Weight decay      137
Weights, geometrical meaning of weights      14 16 280—283
Weights, initialization      290

О проекте