Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Global exponential stability of continuous-time interval neural networks.

Sanqing Hu1, Jun Wang

  • 1Department of Automation and Computer-Aided Engineering, The Chinese University of Hong Kong, Shatin, New Territories, Hong Kong.

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|March 23, 2002
PubMed
Summary

This study analyzes the global robust stability of continuous-time interval neural networks with uncertain parameters. A new condition ensures stability for diagonally constrained networks, extending to general networks.

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Synthesis and micellization of amphiphilic brush-coil block copolymer based on poly(epsilon-caprolactone) and PEGylated polyphosphoester.

Biomacromolecules·2006
Same author

Intravenous transplantation of mesenchymal stem cells improves cardiac performance after acute myocardial ischemia in female rats.

Transplant international : official journal of the European Society for Organ Transplantation·2006
Same author

[Effects of mechanical tensile stress on the expression of ICAM-1 mRNA in osteoblasts differentiated from rBMSCs].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2006
Same author

[Effects of osteoporosis on experimental tooth movement in aged rats].

Sichuan da xue xue bao. Yi xue ban = Journal of Sichuan University. Medical science edition·2006
Same author

MCALIGN2: faster, accurate global pairwise alignment of non-coding DNA sequences based on explicit models of indel evolution.

BMC bioinformatics·2006
Same author

[Managements of masked mastoiditis].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2006

Area of Science:

  • Control Theory
  • Artificial Intelligence
  • Neural Networks

Background:

  • Interval neural networks (INNs) are susceptible to performance degradation due to parameter uncertainties.
  • Ensuring robust stability is critical for reliable operation of INNs in dynamic environments.

Purpose of the Study:

  • To investigate the global robust stability of continuous-time interval neural networks with time-invariant uncertain parameters.
  • To develop conditions for ensuring exponential stability despite unknown parameter bounds.

Main Methods:

  • Introduction of diagonally constrained interval neural networks.
  • Derivation of a necessary and sufficient condition for global exponential stability in diagonally constrained INNs.
  • Extension of the stability condition to general interval neural networks.

Related Experiment Videos

Main Results:

  • A precise condition for global exponential stability of diagonally constrained INNs was established, independent of non-diagonal parameter bounds.
  • A sufficient condition was derived for the robust stability of general continuous-time interval neural networks.
  • Simulation results validated the theoretical findings.

Conclusions:

  • The proposed methods effectively address the global robust stability of interval neural networks.
  • The findings contribute to the design and analysis of more reliable neural network systems.
  • Further research can explore adaptive control strategies for enhanced robustness.