On the VC dimension of bounded margin classifiers

Machine Learning

Volumn 45, Issue 1, 2001, Pages 33-44

  Hush, Don ^a   Scovel, Clint ^a  

^a LOS ALAMOS NATIONAL LABORATORY   (United States)

Author keywords

Fat shattering; Margin; Regular simplex; Vapnik chervonenkis dimension

Indexed keywords

COMPUTATIONAL COMPLEXITY; ERROR ANALYSIS; FUNCTIONS; LAGRANGE MULTIPLIERS; OPTIMIZATION; VECTORS;

VECTOR MACHINES;

LEARNING SYSTEMS;

EID: 0035478855     PISSN: 08856125     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1010971905232     Document Type: Article

References (13)

1. Scale-sensitive dimensions, uniform convergence, and learnability
2. The sample complexity of pattern classification with neural networks: The size of the weights is more important than the size of the network
3. Generalization performance of support vector machines and other pattern classifiers
4. A tutorial on support vector machines for pattern recognition
5. A decision-theoretic generalization of on-line learning and an application to boosting
6. A note on the scale sensitive dimension of linear bounded functionals in Banach spaces
7. Improved generalization through explicit optimization of margin
8. Structural risk minimization over data-dependent hierarchies