Research article summary (published 29 Sep 2009):

Discriminative learning for dynamic state prediction.

Full Abstract

We consider the problem of predicting a sequence of real-valued multivariate states that are correlated by some unknown dynamics, from a given measurement sequence. Although dynamic systems such as the State-Space Models are popular probabilistic models for the problem, their joint modeling of states and observations, as well as the traditional generative learning by maximizing a joint likelihood may not be optimal for the ultimate prediction goal. In this paper, we suggest two novel discriminative approaches to the dynamic state prediction: 1) learning generative state-space models with discriminative objectives and 2) developing an undirected conditional model. These approaches are motivated by the success of recent discriminative approaches to the structured output classification in discrete-state domains, namely, discriminative training of Hidden Markov Models and Conditional Random Fields (CRFs). Extending CRFs to real multivariate state domains generally entails imposing density integrability constraints on the CRF parameter space, which can make the parameter learning difficult. We introduce an efficient convex learning algorithm to handle this task. Experiments on several problem domains, including human motion and robot-arm state estimation, indicate that the proposed approaches yield high prediction accuracy comparable to or better than state-of-the-art methods.

Author information

Author/s: Kim, Minyoung (M); Pavlovic, Vladimir (V);

Affiliation: Department of Computer Science, Rutgers University, Piscataway, NJ 08854, USA. mikim(-atsign-)cs.rutgers.edu

Journal and publication information

Publication Type: Journal Article; Research Support, U.S. Gov't, Non-P.H.S.

Journal: IEEE transactions on pattern analysis and machine intelligence (IEEE Trans Pattern Anal Mach Intell), published in United States. (Language: eng)

Reference: 2009-Oct; vol 31 (issue 10) : pp 1847-61

Dates: Created 2009/08/21; Completed 2009/10/06;

PMID: 19696454, status: MEDLINE (last retrieval date: 10/6/2009, IMS Date: )

Sourced from the National Library of Medicine. Abstract text and other information may be subject to copyright.

External Links for this article
(including full text providers, if available):

Click Electronic Full-text Provider Links to see options for finding the electronic full text links to this article. Note there may be a subscription or fee required for access to the full text. See our FAQ for information on finding FREE full text articles.

This article may also be located in paper journal collections available in many libraries. Use the Journal and Publication Information above to find the full article.

MeSH headings (categories)

This article was linked to the MESH Headings shown below.

Algorithms Artificial Intelligence Discrimination Learning Humans Locomotion

Markov Chains Models, Theoretical Multivariate Analysis Nonlinear Dynamics Pattern Recognition, Automated - methods

Related articles

These are the highest related articles currently in the database:

• Topology preservation and cooperative learning in identification of multiple model systems. 29 Nov 2008
• Reliable H(infinity) nonuniform sampling fuzzy control for nonlinear systems with time delay. 29 Nov 2008
• Nonlinear scale space with spatially varying stopping time. 29 Nov 2008
• The Q-norm complexity measure and the minimum gradient method: a novel approach to the machine learning structural risk minimization problem. 30 Jul 2008
• Training hard-margin support vector machines using greedy stagewise algorithm. 30 Jul 2008
• Comments on "The extreme learning machine". 30 Jul 2008
• Kernels for generalized multiple-instance learning. 29 Nov 2008
• Incremental isometric embedding of high-dimensional data using connected neighborhood graphs. 30 Dec 2008
• Multilayer Potts perceptrons with Levenberg-Marquardt learning. 29 Nov 2008
• Nesting one-against-one algorithm based on SVMs for pattern classification. 29 Nov 2008

See 100+ related articles.

Related Article Map

Legend: - FREE Full text Article. - Abstract only. - Title only. More help.

See a large map of 100+ related articles.