The nature of statistical learning theory.
[For the review of the first edition from 1995 see Zbl 0833.62008.] The goal of this book is to describe the nature of statistical learning theory. It is not a survey of the standard learning theory but it is intended to show how abstract reasoning implies new algorithms. Ch. 1 is to promote the setting of the learning problem. It presents the classical paradigm of solving learning problems, nonparametric methods of density estimation, and the main principles for solving problems with restricted information. A general model of minimizing the risk functional from empirical data is introduced. Ch. 2 describes the conceptual theory of learning processes: Key theorems of learning theory, theory of nonfalsifiability, and concepts that allow the construction of necessary and sufficient conditions for the consistency of the learning processes. Ch. 3 gives the nonasymptotic theory of distribution-independent and dependent bounds on the convergence rate of the learning processes. Ch. 4 deals with the theory for controlling the generalization ability of learning machines which is founded on constructing an inductive principle for minimizing the risc functional for a small sample size of training instances. (Examples of structures for neural networks, local function approximation, MDL and SRM principles, capacity control). Ch. 5 describes learning algorithms for pattern recognition with generalizations for the regression estimation problem. Along with classical neural networks the minimization of the empirical risc with fixed confidence intervals is implemented. The main topics promote experiments with support vector machines (SVM). Ch. 6 introduces a new type of loss functions, the so-called \(\varepsilon\)-insensitive loss function. The results obtained for the pattern recognition problem are generalized to the problem of estimating real-valued regressions. Ch. 7 shows a new approach to the problems above combining the ideas of the theory of ill-posed problems, classical nonparametric statistics, and statistical learning theory to obtain a new type of algorithms. Ch. 8 introduces a new principle for minimizing the expected risk called the vicinal risk minimization using the SVM technique. The book is not easy-reading but written in a concise style. It must be recommended to scientists of statistics, mathematics, physics, and computer science.
- An algorithm for the recognition of levels of congestion in road traffic problems
- Credit scoring using support vector machines with direct search for parameters selection
- Data gravitation based classification
- Discontinuity detection in multivariate space for stochastic simulations
- A non-probabilistic recognizer of stochastic signals based on KLT
- Interval predictor models: identification and reliability
- Response classification of simple polycrystalline microstructures
- Gaussian kernel optimization for pattern classification
- A simultaneous learning framework for clustering and classification
- Nonlinear measures of association with kernel canonical correlation analysis and applications
- An iterative modified kernel based on training data
- A method for improving the accuracy of data mining classification algorithms
- Selection of artificial neural network models for survival analysis with genetic algorithms
- High-dimensional pseudo-logistic regression and classification with applications to gene expression data
- Robust centroid based classification with minimum error rates for high dimension, low sample size data
- Measurement by subjective estimation: Testing for separable representations
- Classification of gene functions using support vector machine for time-course gene expression data
- Identifying winners of competitive events: a SVM-based classification model for horserace prediction
- Using a similarity measure for credible classification
- Identification of MIMO systems using radial basis function networks with hybrid learning algorithm
- Testability and Ockham's razor: How formal and statistical learning theory converge in the new riddle of induction
- Design of interpretable fuzzy rule-based classifiers using spectral analysis with structure and parameters optimization
- Support vector machines for default prediction of SMEs based on technology credit
- The theoretical fundamentals of learning theory based on fuzzy complex random samples
- Maximal width learning of binary functions
- A reference model for customer-centric data mining with support vector machines
- SVM-like decision theoretical classification of high-dimensional vectors
- A multi-class large margin classifier
- Nonlinear multifunctional sensor signal reconstruction based on least squares support vector machines and total least squares algorithm
- SVM-Maj: a majorization approach to linear support vector machines with different hinge errors
- On convergence proofs in system identification -- a general principle using ideas from learning theory
- An introduction to some statistical aspects of PAC learning theory
- An iterative algorithm learning the maximal margin classifier.
- Enhancing prototype reduction schemes with LVQ3-type algorithms
- Online training of support vector classifier.
- Gauge groups and data classification.
- Principles of nonparametric learning. Papers from the summer school, Udine, Italy, July 9--13, 2001
- Protein function classification via support vector machine approach
- On using prototype reduction schemes to optimize kernel-based nonlinear subspace methods.
- Flexible view recognition for indoor navigation based on Gabor filters and support vector machines.
- Results in statistical discriminant analysis: A review of the former Soviet Union literature.
- Ridge estimation for regression models with crisp inputs and Gaussian fuzzy output.
- Inequalities for uniform deviations of averages from expectations with applications to nonparametric regression
- Smooth discrimination analysis
- Bayesian predictiveness, exchangeability and sufficientness in bacterial taxonomy
- Query by committee, linear separation and random walks.
- On the state of the art in machine learning: A personal review
- Kernel selection with spectral perturbation stability of kernel matrix
- Inference for copula modeling of discrete data: a cautionary tale and some facts
- China's energy consumption forecasting by GMDH based auto-regressive model
- Identifying translation initiation sites in prokaryotes using support vector machine
- Simpler PAC-Bayesian bounds for hostile data
- Perspective functions: properties, constructions, and examples
- Accelerating the branch-and-price algorithm using machine learning
- Principal quantile regression for sufficient dimension reduction with heteroscedasticity
- An SVM-like approach for expectile regression
- Twin SVM with a reject option through ROC curve
- Continuum directions for supervised dimension reduction
- Distance based multiple kernel ELM: a fast multiple kernel learning approach
- A new SVM multiclass incremental learning algorithm
- The cumulative distribution transform and linear pattern classification
- A new class of multi-stable neural networks: stability analysis and learning process
- On spectral windows in supervised learning from data
- Using weighted least squares to approximate the discriminant function with a cylindrical surface in classification problems
- Applying two-stage neural network based classifiers to the identification of mixture control chart patterns for an SPC-EPC process
- Machine learning of linear differential equations using Gaussian processes
- European exchange trading funds trading with locally weighted support vector regression
- Hidden physics models: machine learning of nonlinear partial differential equations
- A general framework for predictive tensor modeling with domain knowledge
- Robust \(\epsilon\)-support vector regression
- A robust probability classifier based on the modified \(\chi^2\)-distance
- Integrated use of statistical-based approaches and computational intelligence techniques for tumors classification using microarray
- Angle-based twin support vector machine
- Multiple Bayesian discriminant functions for high-dimensional massive data classification
- A mixed-integer programming approach to GRNN parameter estimation
- An efficient Gaussian kernel optimization based on centered kernel polarization criterion
- Pairwise constraints based multiview features fusion for scene classification
- On the computational power of circuits of spiking neurons
- Gabor filters-based feature extraction for character recognition
- Pursuit of food \textit{versus} pursuit of information in a Markovian perception-action loop model of foraging
- Large-scale linear nonparallel SVMs
- Learning sparse FRAME models for natural image patterns
- Classification by pairwise coupling
- Partitioning points by parallel planes
- Prediction algorithms and confidence measures based on algorithmic randomness theory.
- Converting numerical classification into text classification
- Improved lower bounds for learning from noisy examples: An information-theoretic approach
- Learning and generalisation. With applications to neural networks.
- Image processing with neural networks -- a review
- Robust vision-based features and classification schemes for off-line handwritten digit recognition
- Support vector machines are universally consistent
- A new test for randomness and its application to some cryptographic problems
- Statistical learning theory and stochastic optimization. Ecole d'Eté de Probabilitiés de Saint-Flour XXXI -- 2001.
- Robust learning -- rich and poor
- Stability of continuous value discretisation: an application within rough set theory
- Probabilistic quickest path algorithm
- On data classification by iterative linear partitioning
- Some connections between learning and optimization
- Alternative linear discriminant classifier
- Leave one support vector out cross validation for fast estimation of generalization errors
This page was built for publication: The nature of statistical learning theory.
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4935997)
