Research article summary (published 30 Jul 2008):

The Q-norm complexity measure and the minimum gradient method: a novel approach to the machine learning structural risk minimization problem.

Full Abstract

This paper presents a novel approach for dealing with the structural risk minimization (SRM) applied to a general setting of the machine learning problem. The formulation is based on the fundamental concept that supervised learning is a bi-objective optimization problem in which two conflicting objectives should be minimized. The objectives are related to the empirical training error and the machine complexity. In this paper, one general Q-norm method to compute the machine complexity is presented, and, as a particular practical case, the minimum gradient method (MGM) is derived relying on the definition of the fat-shattering dimension. A practical mechanism for parallel layer perceptron (PLP) network training, involving only quasi-convex functions, is generated using the aforementioned definitions. Experimental results on 15 different benchmarks are presented, which show the potential of the proposed ideas.

Author information

Author/s: Vieira, D A G (DA); Takahashi, Ricardo H C (RH); Palade, Vasile (V); Vasconcelos, J A (JA); Caminhas, W M (WM);

Affiliation: Department of Electrical Engineering, Federal University of Minas Gerais, Belo Horizonte, MG 31270-010, Brazil. douglas(-atsign-)cpdee.ufmg.br

Journal and publication information

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

Journal: IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council (IEEE Trans Neural Netw), published in United States. (Language: eng)

Reference: 2008-Aug; vol 19 (issue 8) : pp 1415-30

Dates: Created 2008/08/14; Completed 2008/10/24; Revised 2009/10/28;

PMID: 18701371, status: MEDLINE (last retrieved date: 10/28/2009)

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 (categories) shown below.

Algorithms Artificial Intelligence Computer Simulation

Models, Theoretical Neural Networks (Computer) Pattern Recognition, Automated - methods

Note: Bold headings indicate primary MeSH headings or qualifiers.

Related articles

These are the most related articles currently in our database:

• Formulation and integration of learning differential equations on the stiefel manifold. 30 Oct 2005
• Analysis of the initial values in split-complex backpropagation algorithm. 30 Aug 2008
• Training hard-margin support vector machines using greedy stagewise algorithm. 30 Jul 2008
• Dynamics of learning in multilayer perceptrons near singularities. 30 Jul 2008
• Global robust stability of bidirectional associative memory neural networks with multiple time delays. 29 Sep 2007
• Adaptive predictive control using neural network for a class of pure-feedback systems in discrete time. 30 Aug 2008
• Accuracy/diversity and ensemble MLP classifier design. 30 Aug 2006
• Analysis of artificial neural networks for pattern-based adaptive control. 30 Aug 2006
• Global exponential stability of multitime scale competitive neural networks with nonsmooth functions. 30 Aug 2006
• Visualization of tree-structured data through generative topographic mapping. 30 Jul 2008

See 100+ related articles.

Related Article Map

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

See a larger map of 100+ related articles.