scispace - formally typeset
Search or ask a question
Topic

Statistical learning theory

About: Statistical learning theory is a research topic. Over the lifetime, 1618 publications have been published within this topic receiving 158033 citations.


Papers
More filters
Book ChapterDOI
Tie-Yan Liu1
01 Jan 2011
TL;DR: This chapter gives the big picture of theoretical analysis for ranking, and point out several important issues to be investigated: statistical ranking framework, generalization ability, and statistical consistency for ranking methods.
Abstract: In this chapter, we introduce the statistical learning theory for ranking In order to better understand existing learning-to-rank algorithms, and to design better algorithms, it is very helpful to deeply understand their theoretical properties In this chapter, we give the big picture of theoretical analysis for ranking, and point out several important issues to be investigated: statistical ranking framework, generalization ability, and statistical consistency for ranking methods

2 citations

Journal ArticleDOI
TL;DR: In this paper, a new method for land use classification from remote sensing image based on Support Vector Machine (SVM) and Soectoal Similarity Scale (SSS) is presented.
Abstract: A new method for land use classification from remote sensing image based on Support Vector Machine(SVM) and Soectoal Similarity Scale(SSS) is presented.The SSS is used to determine spectral similarity by simultaneously measuring the size and shape between two spectrum.SVM,a machine learning algorithm which is based on statistical learning theory,is characteristic in solving limit samples,non-linear and high dimension model recognizing problems,and can be largely used in other arears.Firstly by field investigation,interest region then is set up on the remote sensing image using accurate boundary lines.Select some training sample points and then draw the samples which have been purified to make a sample reference spectrum corresponding with the image's spectrum of each wave band.By drawing some amount of training samples using SSS and constructing classifies using SVM,the land use classification to the whole remote sensing image then can be done.Based on the landsat 7 ETM+ data and ground true data,the paper takes Putian city as interest region for land use classification using SSS and compares its result with that of MLC.Randomly selecting 200 sample points from each type,it can be seen from the two result images that the precision of this method has reached 89.5%,7.9% higher than that of MLC.The classification speed has also been improved obviously.It has obvious superiority and application prospect.

2 citations

Journal ArticleDOI
TL;DR: SVM and its applications in chaotic timeseries including predicting chaotic time series, focus on comparison in regression type selection, and kernel type selection in the same regression machine type.
Abstract: Support Vector Machines (SVM), which is a new generation learning method based on advances in statistical learning theory, is characterized by the use of many standard technologies of machine learning such as maximal margin hyperplane, Mercel kernels and the quadratic programming. Because the best performance is obtained in many currently challenging applications, SVM has sustained wide attention, and has been become the standard tools of machine learning and data mining. But as a developing technology, SVM still have some problems and its applications are limited. In this paper, SVM and its applications in chaotic time series including predicting chaotic time series, focus on comparison in regression type selection, and kernel type selection in the same regression machine type.

2 citations

26 Apr 2012
TL;DR: This paper shows how probabilistic methods and statistical learning theory can provide approximate solutions to “difficult” control problems and introduces bootstrap learning methods to drastically reduce the bound on the number of samples required to achieve a performance level.
Abstract: This paper shows how probabilistic methods and statistical learning theory can provide approximate solutions to “difficult” control problems. The paper also introduces bootstrap learning methods to drastically reduce the bound on the number of samples required to achieve a performance level. These results are then applied to obtain more efficient algorithms which probabilistically guarantee stability and robustness levels when designing controllers for uncertain systems. The paper includes examples of the applications of these methods.

2 citations

Proceedings ArticleDOI
TL;DR: A learning algorithm to classify data with nonlinear characteristics by mapping the input vectors x into a high-dimensional feature space Z through some nonlinear mapping, chosen a priori.
Abstract: The purpose of this paper is to present a learning algorithm to classify data with nonlinear characteristics. The support vector (SV) algorithm is a novel type of learning machine based on statistical learning theory (Vapnik, 1998). The support vector (SV) machine implements the following idea: It maps the input vectors x into a high-dimensional feature space Z through some nonlinear mapping, chosen a priori. In this space, an optimal separating hyperplane is constructed to separate data groupings.

2 citations


Network Information
Related Topics (5)
Artificial neural network
207K papers, 4.5M citations
86% related
Cluster analysis
146.5K papers, 2.9M citations
82% related
Feature extraction
111.8K papers, 2.1M citations
81% related
Optimization problem
96.4K papers, 2.1M citations
80% related
Fuzzy logic
151.2K papers, 2.3M citations
79% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20239
202219
202159
202069
201972
201847