Document Detail


Design of recurrent neural networks for solving constrained least absolute deviation problems.
MedLine Citation:
PMID:  20562048     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Recurrent neural networks for solving constrained least absolute deviation (LAD) problems or L(1)-norm optimization problems have attracted much interest in recent years. But so far most neural networks can only deal with some special linear constraints efficiently. In this paper, two neural networks are proposed for solving LAD problems with various linear constraints including equality, two-sided inequality and bound constraints. When tailored to solve some special cases of LAD problems in which not all types of constraints are present, the two networks can yield simpler architectures than most existing ones in the literature. In particular, for solving problems with both equality and one-sided inequality constraints, another network is invented. All of the networks proposed in this paper are rigorously shown to be capable of solving the corresponding problems. The different networks designed for solving the same types of problems possess the same structural complexity, which is due to the fact these architectures share the same computing blocks and only differ in connections between some blocks. By this means, some flexibility for circuits realization is provided. Numerical simulations are carried out to illustrate the theoretical results and compare the convergence rates of the networks.
Authors:
Xiaolin Hu; Changyin Sun; Bo Zhang
Related Documents :
6232248 - Health professionals' patterns of communication: cross-purpose or problem solving?
11508458 - Resolution of two-way data: theoretical background and practical problem-solving. part ...
19747038 - A fast and exact algorithm for the median of three problem: a graph decomposition appro...
15903478 - Distance-d covering problems in scale-free networks with degree correlations.
16809528 - Would you be happier if you were richer? a focusing illusion.
18468278 - Sensitivity and bias under conditions of equal and unequal academic task difficulty.
Publication Detail:
Type:  Journal Article; Research Support, Non-U.S. Gov't     Date:  2010-06-17
Journal Detail:
Title:  IEEE transactions on neural networks / a publication of the IEEE Neural Networks Council     Volume:  21     ISSN:  1941-0093     ISO Abbreviation:  IEEE Trans Neural Netw     Publication Date:  2010 Jul 
Date Detail:
Created Date:  2010-07-27     Completed Date:  2010-11-12     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  101211035     Medline TA:  IEEE Trans Neural Netw     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1073-86     Citation Subset:  IM    
Affiliation:
State Key Laboratory of Intelligent Technology and Systems, TNList, and the Department of Computer Science and Technology, Tsinghua University, Beijing 100084, China. xiaolin.hu@gmail.com
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Algorithms*
Computer Simulation
Humans
Neural Networks (Computer)*
Nonlinear Dynamics
Pattern Recognition, Automated / methods*

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine


Previous Document:  An Augmented LKF Approach Involving Derivative Information of Both State and Delay.
Next Document:  Electrical Stimulation of the Rectus Femoris During Pre-Swing Diminishes Hip and Knee Flexion During...