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

Second-order neural nets for constrained optimization.

S Zhang1, X Zhu, L H Zou

  • 1Exper Vision Inc., San Jose, CA.

IEEE Transactions on Neural Networks
|January 1, 1992
PubMed
Summary
This summary is machine-generated.

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

[Serum metabonomics study on Cr (Ⅵ ) subchronic exposure rats based on UPLC-Q-TOF-MS/MS platform].

Zhonghua lao dong wei sheng zhi ye bing za zhi = Zhonghua laodong weisheng zhiyebing zazhi = Chinese journal of industrial hygiene and occupational diseases·2020
Same author

The expression changes and correlation analysis of high mobility group box-1 and tissue factor in the serum of rats with sepsis.

European review for medical and pharmacological sciences·2019
Same author

[Expression of PAI-2 mRNA in peripheral blood leucocytes and regulation by sGC activator in pulmonary hypertension].

Zhonghua yi xue za zhi·2016
Same author

[Association between OR2T3 gene and pulmonary arterial hypertension].

Zhonghua yi xue za zhi·2016
Same author

Microvascular autologous submandibular gland transfer in severe cases of keratoconjunctivitis sicca.

International journal of oral and maxillofacial surgery·2004
Same author

Type IB secretory phospholipase A2 is contained in insulin secretory granules of pancreatic islet beta-cells and is co-secreted with insulin from glucose-stimulated islets.

Biochimica et biophysica acta·1998
Same journal

Universal perceptron and DNA-like learning algorithm for binary neural networks: LSBF and PBF implementations.

IEEE transactions on neural networks·2013
Same journal

Guest editorial: special section on white box nonlinear prediction models.

IEEE transactions on neural networks·2011
Same journal

Data-based fault-tolerant control of high-speed trains with traction/braking notch nonlinearities and actuator failures.

IEEE transactions on neural networks·2011
Same journal

Guest editorial: special section on data-based control, modeling, and optimization.

IEEE transactions on neural networks·2011
Same journal

Neural network-based multiple robot simultaneous localization and mapping.

IEEE transactions on neural networks·2011
Same journal

Data-driven model-free adaptive control for a class of MIMO nonlinear discrete-time systems.

IEEE transactions on neural networks·2011
See all related articles

Analog neural networks offer a stable approach to solving constrained optimization problems, mirroring Newton's algorithm. These networks can handle discrete variables for combinatorial optimization tasks.

Area of Science:

  • Computational neuroscience
  • Numerical analysis
  • Optimization theory

Background:

  • Constrained optimization problems are prevalent in various scientific and engineering fields.
  • Traditional numerical methods can face challenges with stability and convergence for certain optimization problems.

Purpose of the Study:

  • To propose analog neural networks as a novel approach for solving constrained optimization problems.
  • To demonstrate the global stability and convergence properties of the proposed neural model.
  • To extend the applicability of neural networks to combinatorial optimization problems with discrete variables.

Main Methods:

  • Development of an analog neural network model inspired by Newton's algorithm.
  • Introduction of nonlinear neurons to handle discrete variable optimization.

Related Experiment Videos

  • Analysis of the model's stability and convergence characteristics.

    • Main Results:

    • The proposed analog neural network model exhibits global stability.
    • The model is capable of converging to constrained stationary points.
    • The inclusion of nonlinear neurons enables the solution of combinatorial optimization problems.

    Conclusions:

    • Analog neural networks provide a robust and stable framework for constrained optimization.
    • The model's ability to handle discrete variables opens new avenues for solving complex combinatorial problems.
    • This approach offers a promising alternative to traditional numerical methods in optimization.