Document Detail


Invariant set of weight of perceptron trained by perceptron training algorithm.
MedLine Citation:
PMID:  20199935     Owner:  NLM     Status:  In-Process    
Abstract/OtherAbstract:
In this paper, an invariant set of the weight of the perceptron trained by the perceptron training algorithm is defined and characterized. The dynamic range of the steady-state values of the weight of the perceptron can be evaluated by finding the dynamic range of the weight of the perceptron inside the largest invariant set. In addition, the necessary and sufficient condition for the forward dynamics of the weight of the perceptron to be injective, as well as the condition for the invariant set of the weight of the perceptron to be attractive, is derived.
Authors:
Charlotte Yuk-Fan Ho; Bingo Wing-Kuen Ling; Herbert Ho-Ching Iu
Related Documents :
1564015 - Application of ultrasound for genetic improvement.
8909095 - Participation in multicomponent hypnosis treatment programs for women's weight loss wit...
20827875 - Prevalence and trends in obesity among mississippi public school students, 2005-2009.
18255665 - On convergence properties of pocket algorithm.
20428705 - Competency-based curriculum and active methodology: perceptions of nursing students.
12900345 - Cost effectiveness of defibrillation by targeted responders in public settings.
Publication Detail:
Type:  Journal Article     Date:  2010-03-01
Journal Detail:
Title:  IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics : a publication of the IEEE Systems, Man, and Cybernetics Society     Volume:  40     ISSN:  1941-0492     ISO Abbreviation:  IEEE Trans Syst Man Cybern B Cybern     Publication Date:  2010 Dec 
Date Detail:
Created Date:  2010-11-16     Completed Date:  -     Revised Date:  -    
Medline Journal Info:
Nlm Unique ID:  9890044     Medline TA:  IEEE Trans Syst Man Cybern B Cybern     Country:  United States    
Other Details:
Languages:  eng     Pagination:  1521-30     Citation Subset:  IM    
Affiliation:
School of Mathematical Sciences, Queen Mary,University of London, E14NS London, UK. c.ho@qmul.ac.uk
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:

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


Previous Document:  Neural Mechanisms of the Mind, Aristotle, Zadeh, and fMRI.
Next Document:  Low-resolution gait recognition.