Measuring the VC-dimension of a learning machine
Neural Computation
Machine Learning
Making large-scale support vector machine learning practical
Advances in kernel methods
Evaluating the Generalization Ability of Support Vector Machines through the Bootstrap
Neural Processing Letters
A vector space model for automatic indexing
Communications of the ACM
Model Selection and Error Estimation
Machine Learning
Rademacher and gaussian complexities: risk bounds and structural results
The Journal of Machine Learning Research
A study of cross-validation and bootstrap for accuracy estimation and model selection
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Semi-Supervised Learning
IEEE Transactions on Information Theory - Part 2
IEEE Transactions on Neural Networks
K-winner machines for pattern classification
IEEE Transactions on Neural Networks
Mercer kernel-based clustering in feature space
IEEE Transactions on Neural Networks
Behavior-constrained support vector machines for fMRI data analysis
IEEE Transactions on Neural Networks
Mixing linear SVMs for nonlinear classification
IEEE Transactions on Neural Networks
Hi-index | 0.00 |
A crucial issue in designing learning machines is to select the correct model parameters. When the number of available samples is small, theoretical sample-based generalization bounds can prove effective, provided that they are tight and track the validation error correctly. The maximal discrepancy (MD) approach is a very promising technique for model selection for support vector machines (SVM), and estimates a classifier's generalization performance by multiple training cycles on random labeled data. This paper presents a general method to compute the generalization bounds for SVMs, which is based on referring the SVM parameters to an unsupervised solution, and shows that such an approach yields tight bounds and attains effective model selection. When one estimates the generalization error, one uses an unsupervised reference to constrain the complexity of the learning machine, thereby possibly decreasing sharply the number of admissible hypothesis. Although the methodology has a general value, the method described in the paper adopts vector quantization (VQ) as a representation paradigm, and introduces a biased regularization approach in bound computation and learning. Experimental results validate the proposed method on complex real-world data sets.