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

Pattern recognition using asymmetric attractor neural networks.

Tao Jin1, Hong Zhao

  • 1Physics Department of Lanzhou University, Lanzhou 730000, China.

Physical Review. E, Statistical, Nonlinear, and Soft Matter Physics
|February 21, 2006
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

[Evaluation of palatal bone thickness in adults with normal occlusion for orthodontic miniscrews placement].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2011
Same author

5-Methyl-1-(3-nitro-benz-yl)-1H-1,2,3-triazole-4-carboxylic acid monohydrate.

Acta crystallographica. Section E, Structure reports online·2011
Same author

1-Benzyl-5-methyl-1H-1,2,3-triazole-4-carboxylic acid monohydrate.

Acta crystallographica. Section E, Structure reports online·2011
Same author

1-[(3-Methyl-piperidin-1-yl)(phen-yl)meth-yl]-2-naphthol.

Acta crystallographica. Section E, Structure reports online·2011
Same author

3-[(1H-Benzimidazol-2-yl)sulfanyl-methyl]benzonitrile.

Acta crystallographica. Section E, Structure reports online·2011
Same author

Determination of fumaric and maleic acids with stacking analytes by transient moving chemical reaction boundary method in capillary electrophoresis.

Journal of chromatography. A·2011
Same journal

Tension on dsDNA bound to ssDNA-RecA filaments may play an important role in driving efficient and accurate homology recognition and strand exchange.

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Amplitude-phase coupling drives chimera states in globally coupled laser networks [Phys. Rev. E 91, 040901(R) (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Erratum: Shapes of sedimenting soft elastic capsules in a viscous fluid [Phys. Rev. E 92, 033003 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Erratum: Attenuation of excitation decay rate due to collective effect [Phys. Rev. E 90, 022142 (2014)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Role of connectivity and fluctuations in the nucleation of calcium waves in cardiac cells [Phys. Rev. E 92, 052715 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
Same journal

Publisher's Note: Lattice Boltzmann approach for complex nonequilibrium flows [Phys. Rev. E 92, 043308 (2015)].

Physical review. E, Statistical, nonlinear, and soft matter physics·2016
See all related articles

Asymmetric attractor neural networks effectively recognize patterns by using controlled "islands" within a chaotic sea. This method identifies known patterns and rejects unknown ones, enhancing pattern recognition capabilities.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Attractor neural networks are promising for pattern recognition.
  • Asymmetric networks with low symmetry exhibit unique attractor properties.
  • Monte Carlo (MC) adaptation rules can design these networks.

Purpose of the Study:

  • To develop an effective method for pattern recognition and rejection using asymmetric attractor neural networks.
  • To demonstrate how controlled attraction basins can be utilized for classification.
  • To explore the role of the MC-adaptation rule in enhancing network performance.

Main Methods:

  • Storing template patterns as fixed-point attractors in asymmetric neural networks.
  • Utilizing isolated attraction basins ('islands') within a chaotic sea for pattern identification.

Related Experiment Videos

  • Implementing a threshold-based system for pattern attraction or rejection.
  • Employing a modified MC-adaptation rule to enlarge attraction basin sizes.

    • Main Results:

    • The network successfully distinguishes between known and unknown patterns.
    • Pattern recognition accuracy is linked to the size and control of attraction basins.
    • The modified MC-adaptation rule significantly increases the capacity of the network.
    • Demonstrated effectiveness using Chinese character recognition as an example.

    Conclusions:

    • Asymmetric attractor neural networks offer a robust framework for pattern recognition and rejection.
    • The control over attraction basin size is crucial for effective classification.
    • The MC-adaptation rule plays a key role in optimizing network performance for pattern recognition.