A Probabilistic Theory of Pattern RecognitionSpringer Science & Business Media, 20.2.1997 - 638 sivua Pattern recognition presents one of the most significant challenges for scientists and engineers, and many different approaches have been proposed. The aim of this book is to provide a self-contained account of probabilistic analysis of these approaches. The book includes a discussion of distance measures, nonparametric methods based on kernels or nearest neighbors, Vapnik-Chervonenkis theory, epsilon entropy, parametric classification, error estimation, free classifiers, and neural networks. Wherever possible, distribution-free properties and inequalities are derived. A substantial portion of the results or the analysis is new. Over 430 problems and exercises complement the material. |
Kirjan sisältä
Tulokset 1 - 5 kokonaismäärästä 84
Sivu x
... Empirical Risk Minimization 49 4.6 Minimizing Other Criteria 54 Problems and Exercises 56 5 Nearest Neighbor Rules 61 5.1 Introduction 61 5.2 Notation and Simple Asymptotics 63 5.3 Proof of Stone's Lemma 66 5.4 The Asymptotic Probability of ...
... Empirical Risk Minimization 49 4.6 Minimizing Other Criteria 54 Problems and Exercises 56 5 Nearest Neighbor Rules 61 5.1 Introduction 61 5.2 Notation and Simple Asymptotics 63 5.3 Proof of Stone's Lemma 66 5.4 The Asymptotic Probability of ...
Sivu xi
Luc Devroye, László Györfi, Gabor Lugosi. 8.5 Estimating the Bayes Error 128 Problems and Exercises 129 9 The Regular ... Empirical Error Minimization 187 12.2 Fingering 191 12.3 The Glivenko-Cantelli Theorem 192 12.4 Uniform Deviations ...
Luc Devroye, László Györfi, Gabor Lugosi. 8.5 Estimating the Bayes Error 128 Problems and Exercises 129 9 The Regular ... Empirical Error Minimization 187 12.2 Fingering 191 12.3 The Glivenko-Cantelli Theorem 192 12.4 Uniform Deviations ...
Sivu xii
... Problems and Exercises 261 16 Parametric Classification 263 16.1 Example: Exponential Families 266 16.2 Standard Plug-In Rules 267 16.3 Minimum Distance Estimates 270 16.4 Empirical Error Minimization 275 Problems and Exercises 276 17 ...
... Problems and Exercises 261 16 Parametric Classification 263 16.1 Example: Exponential Families 266 16.2 Standard Plug-In Rules 267 16.3 Minimum Distance Estimates 270 16.4 Empirical Error Minimization 275 Problems and Exercises 276 17 ...
Sivu xiv
... Problems and Exercises 486 29 Uniform Laws of Large Numbers 489 29.1 Minimizing the Empirical Squared Error 489 29.2 Uniform Deviations of Averages from Expectations 490 29.3 Empirical Squared Error Minimization 493 29.4 Proof of ...
... Problems and Exercises 486 29 Uniform Laws of Large Numbers 489 29.1 Minimizing the Empirical Squared Error 489 29.2 Uniform Deviations of Averages from Expectations 490 29.3 Empirical Squared Error Minimization 493 29.4 Proof of ...
Sivu 43
Valitettavasti tämän sivun sisältö on rajoitettu.
Valitettavasti tämän sivun sisältö on rajoitettu.
Sisältö
Introduction | 1 |
The Bayes Error | 9 |
Inequalities and Alternate Distance Measures | 21 |
Linear Discrimination | 39 |
Nearest Neighbor Rules | 61 |
Consistency | 91 |
Slow Rates of Convergence | 111 |
Error Estimation | 121 |
Tree Classifiers | 315 |
DataDependent Partitioning | 363 |
Splitting the Data | 387 |
The Resubstitution Estimate | 397 |
Deleted Estimates of the Error Probability | 407 |
Automatic Kernel Rules | 423 |
Automatic Nearest Neighbor Rules | 451 |
Hypercubes and Discrete Spaces | 461 |
The Regular Histogram Rule | 133 |
Kernel Rules | 147 |
Consistency of the fcNearest Neighbor Rule | 169 |
VapnikChervonenkis Theory | 187 |
Combinatorial Aspects of VapnikChervonenkis Theory | 215 |
Lower Bounds for Empirical Classifier Selection | 233 |
The Maximum Likelihood Principle | 249 |
Parametric Classification | 263 |
Generalized Linear Discrimination | 279 |
Complexity Regularization | 289 |
Condensed and Edited Nearest Neighbor Rules | 303 |
Epsilon Entropy and Totally Bounded Sets | 479 |
Uniform Laws of Large Numbers | 489 |
Neural Networks | 507 |
Other Error Estimates | 549 |
Feature Extraction | 561 |
Appendix | 575 |
Notation | 591 |
619 | |
627 | |
Muita painoksia - Näytä kaikki
A Probabilistic Theory of Pattern Recognition Luc Devroye,Laszlo Györfi,Gabor Lugosi Rajoitettu esikatselu - 2013 |
A Probabilistic Theory of Pattern Recognition Luc Devroye,Laszlo Gyorfi,Gábor Lugosi Esikatselu ei käytettävissä - 2014 |
A Probabilistic Theory of Pattern Recognition Luc Devroye,László Györfi,Gabor Lugosi Esikatselu ei käytettävissä - 2013 |
Yleiset termit ja lausekkeet
apply Assume Bayes bound called cells Chapter classification rule classifier Clearly close coefficients complexity components computational Consider constant contains continuous convergence corresponding covering cuts decision defined definition denotes density depends discrimination distance distribution empirical error error probability estimate example exists expected fact Figure finite fixed function given hyperplane implies independent inequality integer introduce Lemma linear measure method minimizing nearest neighbor rule Note Observe obtained otherwise pairs parameters partition performance pick points positive possible probability of error Problem proof Prove random variables rectangles regions Remark respect result risk sample satisfies selected sequence shatter Show simple smoothing space split subsets suffices term Theorem tree uniform universally consistent upper bound values vc dimension vector weights zero