Please use this identifier to cite or link to this item:
https://hdl.handle.net/20.500.14279/8209
Title: | Infinite markov-switching maximum entropy discrimination machines | Authors: | Chatzis, Sotirios P. | Major Field of Science: | Engineering and Technology | Field Category: | Electrical Engineering - Electronic Engineering - Information Engineering | Keywords: | Bayesian nonparametrics;Dirichlet process models;Maximum entropy discrimination | Issue Date: | 2013 | Source: | Journal of Machine Learning Research: Workshop and Conference Proceedings, 2013, vol. 28, no. 3, pp. 729-737 | Volume: | 28 | Issue: | 3 | Start page: | 729 | End page: | 737 | Link: | http://www.jmlr.org/proceedings/papers/v28/chatzis13.pdf | Journal: | Journal of Machine Learning Research | Abstract: | In this paper, we present a method that combines the merits of Bayesian nonparametrics, specifically stick-breaking priors, and largemargin kernel machines in the context of sequential data classification. The proposed model employs a set of (theoretically) infinite interdependent large-margin classifiers as model components, that robustly capture local nonlinearity of complex data. The employed large-margin classifiers are connected in the context of a Markov-switching construction that allows for capturing complex temporal dynamics in the modeled datasets. Appropriate stick-breaking priors are imposed over the component switching mechanism of our model to allow for data-driven determination of the optimal number of component large-margin classifiers, under a standard nonparametric Bayesian inference scheme. Efficient model training is performed under the maximum entropy discrimination (MED) framework, which integrates the large-margin principle with Bayesian posterior inference. We evaluate our method using several real-world datasets, and compare it to state-of-the-art alternatives. | Description: | Paper presented at 30th International Conference on Machine Learning, 2013, Atlanta, USA, 16 – 21 June. | URI: | https://hdl.handle.net/20.500.14279/8209 | ISSN: | 19387228 | Rights: | © The author(s) | Type: | Article | Affiliation : | Cyprus University of Technology |
Appears in Collections: | Άρθρα/Articles |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Chatzis.pdf | 2.88 MB | Adobe PDF | View/Open |
CORE Recommender
Page view(s) 20
420
Last Week
3
3
Last month
31
31
checked on Apr 27, 2024
Download(s) 50
73
checked on Apr 27, 2024
Google ScholarTM
Check
Items in KTISIS are protected by copyright, with all rights reserved, unless otherwise indicated.