|Subject Domain (in DDC)||Computer science, information & general works ♦ Data processing & computer science|
|Subject Keyword||New Observation ♦ Class Classification Problem ♦ Main Technical Difficulty ♦ Abstract Uniform Entropy Condition ♦ Generalization Ability ♦ Separate Section ♦ Support Vector Machine ♦ Weak Classifier ♦ New Bound ♦ New Zero-error Bound ♦ Vc Class ♦ Zero Error Version ♦ Generalization Error ♦ Sample Size ♦ Weak Classifier Consists ♦ Vc-subgraph Class ♦ Training Set ♦ Toy Problem ♦ Voting Algorithm ♦ Several Direction ♦ Empirical Distribution|
|Description||In this paper we prove new bounds for the generalization error of voting learning algorithms such as boosting, bagging or support vector machines in the framework of two class classification problem. This paper continues the line of research pioneered in the work of Schapire et al. who explained the generalization ability of voting classifiers via the empirical distribution of the margin and the complexity of the family of weak classifiers. In this paper we extend their result in several directions. First of all, we prove a zero error version of their bound which significantly improves the dependence of the bound on all parameters such as sample size. Secondly, we consider the case when the set of weak classifiers consists of real valued uniformly bounded functions and satis es some abstract uniform entropy condition, for example, when the set of weak classifiers is a VC-subgraph class of functions. This is the main technical difficulty of the paper, compared to an easier case of VC classes of sets that was considered in the work of Schapire et al. We consider VC classes of sets in a separate section together with some new observations about families of weak classifiers that depend on the training set. We also incorporate some measure of the sparsity of representation of a combined classifier into the bound. Finally, we experiment with two toy problems to study the performance of the bounds.|
|Educational Role||Student ♦ Teacher|
|Age Range||above 22 year|
|Education Level||UG and PG ♦ Career/Technical Study|
|Learning Resource Type||Article|
|Publisher Institution||In Proceedings of the Thirteenth Na-tional Conference on Artificial Intelligence|
National Digital Library of India (NDLI) is a virtual repository of learning resources which is not just a repository with search/browse facilities but provides a host of services for the learner community. It is sponsored and mentored by Ministry of Education, Government of India, through its National Mission on Education through Information and Communication Technology (NMEICT). Filtered and federated searching is employed to facilitate focused searching so that learners can find the right resource with least effort and in minimum time. NDLI provides user group-specific services such as Examination Preparatory for School and College students and job aspirants. Services for Researchers and general learners are also provided. NDLI is designed to hold content of any language and provides interface support for 10 most widely used Indian languages. It is built to provide support for all academic levels including researchers and life-long learners, all disciplines, all popular forms of access devices and differently-abled learners. It is designed to enable people to learn and prepare from best practices from all over the world and to facilitate researchers to perform inter-linked exploration from multiple sources. It is developed, operated and maintained from Indian Institute of Technology Kharagpur.
NDLI is a conglomeration of freely available or institutionally contributed or donated or publisher managed contents. Almost all these contents are hosted and accessed from respective sources. The responsibility for authenticity, relevance, completeness, accuracy, reliability and suitability of these contents rests with the respective organization and NDLI has no responsibility or liability for these. Every effort is made to keep the NDLI portal up and running smoothly unless there are some unavoidable technical issues.
Ministry of Education, through its National Mission on Education through Information and Communication Technology (NMEICT), has sponsored and funded the National Digital Library of India (NDLI) project.
For any issue or feedback, please write to firstname.lastname@example.org