The nature of statistical learning theory
The nature of statistical learning theory
Exploiting generative models in discriminative classifiers
Proceedings of the 1998 conference on Advances in neural information processing systems II
Using the Fisher Kernel Method to Detect Remote Protein Homologies
Proceedings of the Seventh International Conference on Intelligent Systems for Molecular Biology
On-Line Handwriting Recognition with Support Vector Machines " A Kernel Approach
IWFHR '02 Proceedings of the Eighth International Workshop on Frontiers in Handwriting Recognition (IWFHR'02)
A Generic Approach for On-Line Handwriting Recognition
IWFHR '04 Proceedings of the Ninth International Workshop on Frontiers in Handwriting Recognition
Online Handwritten Shape Recognition Using Segmental Hidden Markov Models
IEEE Transactions on Pattern Analysis and Machine Intelligence
Discriminative learning for minimum error classification [patternrecognition]
IEEE Transactions on Signal Processing
Large margin hidden Markov models for speech recognition
IEEE Transactions on Audio, Speech, and Language Processing
Object classification by fusing SVMs and Gaussian mixtures
Pattern Recognition
Hi-index | 0.01 |
This paper focuses on learning recognition systems able to cope with sequential data for classification and segmentation tasks. It investigates the integration of discriminant power in the learning of generative models, which are usually used for such data. Based on a procedure that transforms a sample data into a generative model, learning is viewed as the selection of efficient component models in a mixture of generative models. This may be done through the learning of a support vector machine. We propose a few kernels for this and report experimental results for classification and segmentation tasks.