Bounding the Fat Shattering Dimension of a Composition Function Class Built Using a Continuous Logic Connective
Hubert Haoyang DuanPublished in: CoRR (2011)
Keyphrases
- fat shattering
- convex combinations
- vapnik chervonenkis dimension
- real valued functions
- covering numbers
- vc dimension
- inductive inference
- kernel machines
- generalization bounds
- uniform convergence
- complexity measures
- convex hull
- learning machines
- gaussian kernels
- upper bound
- boosting algorithms
- function classes
- loss function
- kernel function
- theoretical analysis
- semi supervised