Corpus ID: 61153720

Learning Theory and Support Vector Machines - a primer

@article{Banf2019LearningTA,
  title={Learning Theory and Support Vector Machines - a primer},
  author={Michael Banf},
  journal={ArXiv},
  year={2019},
  volume={abs/1902.04622}
}
  • Michael Banf
  • Published 2019
  • Mathematics, Computer Science
  • ArXiv
  • The main goal of statistical learning theory is to provide a fundamental framework for the problem of decision making and model construction based on sets of data. Here, we present a brief introduction to the fundamentals of statistical learning theory, in particular the difference between empirical and structural risk minimization, including one of its most prominent implementations, i.e. the Support Vector Machine. 

    Figures and Topics from this paper.

    References

    SHOWING 1-10 OF 10 REFERENCES
    Learning with Kernels: support vector machines, regularization, optimization, and beyond
    • 1,190
    • Highly Influential
    • PDF
    The Nature of Statistical Learning Theory
    • V. N. Vapnik
    • Computer Science, Mathematics
    • Statistics for Engineering and Information Science
    • 2000
    • 36,892
    A training algorithm for optimal margin classifiers
    • 9,466
    • PDF
    Probability Estimates for Multi-class Classification by Pairwise Coupling
    • 1,812
    • Highly Influential
    • PDF
    Practical Methods of Optimization
    • 8,667
    • PDF
    Learning with kernels : Support vector machines, regularization, optimization, and beyond
    • 3,217
    • Highly Influential
    A Tutorial on Support Vector Machines for Pattern Recognition
    • 13,219
    • PDF
    Probabilistic Outputs for Support vector Machines and Comparisons to Regularized Likelihood Methods
    • 4,439
    Rozonoer Theoretical Foundations of the Potential Function Method in Pattern Recognition Learning
    • In Automation and Remote Control.,
    • 1964