Suykens J.A.K. - Least Squares Support Vector Machines :: Электронная библиотека попечительского совета мехмата МГУ

Документ взят из кэша поисковой машины. Адрес оригинального документа : http://lib.mexmat.ru/books/74942
Дата изменения: Unknown
Дата индексирования: Mon Apr 11 16:45:42 2016
Кодировка: Windows-1251

Электронная библиотека Попечительского совета
механико-математического факультета
Московского государственного университета

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

Поиск по указателям

Suykens J.A.K. - Least Squares Support Vector Machines

Читать книгу
бесплатно

Скачать книгу с нашего сайта нельзя

Обсудите книгу на научном форуме

Нашли опечатку?
Выделите ее мышкой и нажмите Ctrl+Enter

Название: Least Squares Support Vector Machines

Автор: Suykens J.A.K.

Аннотация:

Focuses on Least Squares Support Vector Machines (LS-SVMs) which are reformulations to standard SVMs. Authors explain the natural links between LS-SVM classifiers and kernel Fisher discriminant analysis.

Язык:

Рубрика: Computer science/

Статус предметного указателя: Готов указатель с номерами страниц

ed2k: ed2k stats

Год издания: 2003

Количество страниц: 294

Добавлена в каталог: 31.10.2010

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

Предметный указатель

$(\beta_{1},\beta_{2})$ -trimmed mean      164
$L_{1}$ estimator      152
$L_{2}$ estimator      152
$\beta$ -trimmed mean      164
$\epsilon$ -tube of accuracy      53
Active selection of support vectors      181
AIC criterion      134
Angles in feature space      61
Automatic relevance determination      21 110 144
Ball and beam control problem      246
Basis construction in feature space      184
Bayes factor      132
Bayes rule      11 14
Bayesian decision theory      14 127
Bayesian inference      11 121
Between class covariance      83
Bias term correction      128
Bias-variance trade-off      11
BIC criterion      134
Bioinformatics applications      63
Breakdown point      156 166
Censored values      165
Centered Gram matrix      129 207
Centered kernel matrix      129 212
Centering matrix      124
chunking      67
Closed-loop stability      238
Committee network      14 190
Committee network extension      196
Committee network of LS-SVMs      191
Compactly supported kernel      61
Complexity of CG method      88
Confusion matrix      19
Conjugate gradient method      87
Consistency      46
Contamination to nominal noise model      150
Contrast function      159
Convex optimization      63
Correlation coefficient      219
Cross-validation      11 156
Curse of dimensionality      4 235
Decision boundary      15
Decomposition      67
Density estimation      181 215
Dimensionality reduction      21 208
Discriminant function      15
Distortion error      21
Double scroll attractor      230
Dual problem      32
Duality gap      66
Effective number of parameters      8 130
Efficiency      167
Efficiency-robustness trade-off      167
Eigenfunctions      175 180 218
Empirical risk      45
Error correcting output codes      81
evidence      11 121
Feature space      36
Finite prediction error criterion      59
Fisher discriminant in feature space      85
Fisher kernel      63
Fixed size LS-SVM      179
Fourier components      103
Gaussian process      106 130
Generalization error      45
Generalized cross-validation criterion      59
Generalized eigenvalue problem      83 219
Generalized prediction error      8
Generalized Rayleigh quotient      224
Grid search for tuning parameters      90
Hampel score function      162
Hetero-skedastic noise      140
Hidden layer      2 36
Huber loss function      161
Hyperparameters      12 121
I/O model      24
Incomplete Cholesky factorization      177
Independent component analysis      224
Influence function      166
Information bottleneck      21 208
Information retrieval      62
Integral equation      217
Interior point algorithms      65
Inverted pendulum      241
Isotropic stationary random field      108
Karhunen - Loeve expansion      217
Kernel CCA      220
Kernel PCA      210
Kernel ridge regression      106
Kernel trick      37
Kernel-target alignment      63
kernels      42
KKT conditions      42
Kriging      108
L-estimators      163
Lagrange multipliers      32
Lagrangian      32
Laplace method      132
Laplacian noise      152
Laplacian prior      69
Lasso estimator      69
Likelihood      12 121
Linear CCA analysis      219
Linear Fisher discriminant analysis      81
Linear least squares      10
Linear PCA analysis      202
Linear PCA analysis with bias term      205
Linear Quadratic Regulator      244
Linear SVM      30
Linearly non-separable case      34
Linearly separable case      31
Logistic activation function      18
Loss function      64
Low rank approximation      175
LP machines      69
LS-SVM classifier      71
LS-SVM function estimation      98
LS-SVM one class PCA      202
M-estimator      158

Margin      30
Marginalization      126
Maximal variance      202
Maximum posterior      122
McCulloch - Pitts model      1
Mercer condition      36
Mercer kernel      36
Microarray data      63
Minimum output coding      81
Model comparison      14 131
Moderated output      127
Moody's criterion      8
Multi-class problem      77
Multilayer network of LS-SVMs      196
Multilayer perceptron      2
N-stage optimal control problem      232
NARX model      24 225
NOE model      24 226
Non-Gaussian noise      155
Non-stationary random field      108
Nonlinear CCA in feature space      222
Nonlinear PCA analysis      21
Nonlinear SVM      37
Normalized kernel      60
Nystroem method      175
Occam factor      132
Occam's razor      13
One-class problem      203
One-step ahead predictor      225
One-versus-all classifier      81
One-versus-one classifier      81
Operations on kernels      60
Optimal brain damage      111
Optimal brain surgeon      111
Optimal LS-SVM controller      234
Order statistics      163
Ordered samples      163
Outliers      156
Overlapping distributions      34
Parametric kernel based model      68
Parametric optimization      68
Partial least squares      224
Parzen window density estimator      218
Path-following method      65
PCA analysis      20
Polynomial model      10
Positive semidefinite kernel      37
Posterior      12 121
Predicted risk      56
Primal problem      32
Principal co-ordinate analysis      205
Prior      12 121
Prior class probability      14 127
Pruning      111
Pseudo inverse matrix      10
QP problem      32
Quantile functional      167
Rayleigh quotient      82
RBF network      23 69
Reconstruction error      208
Recurrent LS-SVM      226
Recurrent neural network      26
Reduced KKT system      66
Reduced set      189
Regularization      8
Renyi entropy      181 218
Representer theorem      105
Reproducing kernel Hilbert spaces      101
Reproducing property      102
Ridge regression      10
Risk      45
Robust cross-validation      168
Robust local stability      239
Robust scale estimator      155
Robust statistics      154
ROC curve      19
Saddle point      32
Score function      159
Score variables      21 203 213
Self-organizing process      182
Sensitivity model      26
Separable      37
Separable correlation function      108
Sequential minimal optimization      67
Sherman - Morrison - Woodbury formula      176
Shibata's model selector      59
Shrinkage estimator      69
Slack variables      35
Sparse representation      181 186
Sparseness      33 111
Spectral representation      108
Spline network      23
Stability of recurrent networks      26
State feedback      233
State space model      26
Stationary random field      108
Statistical learning theory      44
String kernels      62
Structural risk minimization      48
Successive overrelaxation      67
Support vectors      33
Takens' embedding theorem      230
Textmining      62
Transductive inference      183
Trimmed mean      164
Tukey biweight score function      163
UCI benchmarking results      89 136
Unbalanced data set      127
Universal approximation      2
Vapnik $\epsilon$ -insensitive loss function      52
Vapnik's VC bound      56
Variational problem      104
VC bound      49
VC dimension      46
Weight decay      8
Weighted LS-SVM      140 155
Winsorized mean      165
Within class covariance      83
Wolfe dual      66

О проекте