Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

An overview of statistical learning theory.

V N Vapnik1

  • 1AT&T Labs-Research, Red Bank, NJ 07701, USA.

IEEE Transactions on Neural Networks
|February 7, 2008
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Support vector machines for spam categorization.

IEEE transactions on neural networks·2008
Same author

Support vector machines for histogram-based image classification.

IEEE transactions on neural networks·2008
Same author

Model complexity control for regression using VC generalization bounds.

IEEE transactions on neural networks·2008
Same author

[Isolation of a group at risk for stomach cancer based on genetic and epidemiological study data].

Voprosy onkologii·1983
Same author

[Use of a computer in the differential diagnosis of the exophytic form of cancer and benign tumors of the esophagus].

Klinicheskaia meditsina·1977
Same author

[Use of mathematical methods and computers for diagnosis of primary rheumocarditis in children].

Voprosy revmatizma·1975
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Statistical learning theory evolved from abstract concepts to practical applications like support vector machines. This overview explores its theoretical foundations and algorithmic advancements in function estimation.

Area of Science:

  • Computer Science
  • Statistics
  • Machine Learning

Background:

  • Statistical learning theory, initially theoretical, emerged in the late 1960s for function estimation.
  • Until the 1990s, it focused on theoretical analysis of data-driven function estimation problems.
  • The mid-1990s saw the development of practical algorithms, such as support vector machines, based on this theory.

Purpose of the Study:

  • To provide a general overview of statistical learning theory, encompassing both theoretical and algorithmic aspects.
  • To demonstrate how abstract learning theory established generalized conditions for statistical learning.
  • To illustrate how these conditions inspired novel algorithmic approaches to function estimation.

Main Methods:

  • Review of theoretical foundations of statistical learning theory.

Related Experiment Videos

  • Exploration of algorithmic developments, including support vector machines.
  • Analysis of generalization conditions within statistical learning paradigms.

    • Main Results:

    • Statistical learning theory transitioned from pure theory to practical algorithm development.
    • The theory provides generalized conditions for statistical learning and function estimation.
    • Support vector machines exemplify the successful application of the theory.

    Conclusions:

    • Statistical learning theory offers a robust framework for understanding and solving function estimation problems.
    • The integration of theory and algorithms has significantly advanced machine learning capabilities.
    • The principles of statistical learning theory continue to drive innovation in artificial intelligence.