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

Journal article

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 pres...

Expand abstract

Authors: Vieira, D; Takahashi, R; Palade, V; Vasconcelos, J; Caminhas, WM

• Publication status: Published
• Journal: IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council
• Volume: 19
• Issue: 8
• Pages: 1415-1430
• Publication date: 2008-08-01
• DOI: 10.1109/tnn.2008.2000442
• EISSN: 1941-0093
• ISSN: 1045-9227
• Language: English
• Keywords: Pattern Recognition, Automated; Computer Simulation; Models, Theoretical; Neural Networks (Computer); Artificial Intelligence; Algorithms