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

A novel continuous-time neural network for realizing associative memory.

Q Tao1, T Fang, H Qiao

  • 1Hefei Institute of Intelligent Machines, Academia Sinica, Heifei, China.

IEEE Transactions on Neural Networks
|February 5, 2008
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

[Advances in artificial intelligence-based nasal endoscopy in the diagnosis and treatment of rhinologic diseases].

Zhonghua er bi yan hou tou jing wai ke za zhi = Chinese journal of otorhinolaryngology head and neck surgery·2026
Same author

[Progress in epidemiological research of non-traditional risk factors for esophageal cancer].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2026
Same author

Prognostic nomogram for patients with HER2-negative metastatic gastric cancer receiving first-line PD-1 blockade.

ESMO open·2026
Same author

Long-Range Transverse-Momentum Correlations and Radial Flow in Pb-Pb Collisions at the LHC.

Physical review letters·2026
Same author

[Research progress on the lung cancer risk prediction models].

Zhonghua liu xing bing xue za zhi = Zhonghua liuxingbingxue zazhi·2025
Same author

[Numerical considerations for defining a rare disease in China].

Zhonghua kou qiang yi xue za zhi = Zhonghua kouqiang yixue zazhi = Chinese journal of stomatology·2025
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

A novel neural network architecture effectively stores patterns as stable equilibria, offering robust associative memory. This system demonstrates efficient learning, forgetting, and pattern recognition capabilities.

Area of Science:

  • Artificial Intelligence
  • Computational Neuroscience
  • Machine Learning

Background:

  • Developing effective associative memory models is crucial for artificial intelligence and cognitive science.
  • Existing neural network models often face limitations in storage capacity, pattern stability, and learning dynamics.

Purpose of the Study:

  • To introduce a novel neural network for associative memory with enhanced stability and storage.
  • To ensure that stored patterns correspond to asymptotically stable equilibrium points.
  • To analyze the distribution of attraction basins and the network's learning and forgetting capabilities.

Main Methods:

  • The proposed network is a linear system with projection onto a convex set spanned by prototype patterns.
  • Associative memory is realized by ensuring prototype patterns are asymptotically stable equilibrium points.

Related Experiment Videos

  • The network's performance is evaluated through numerical simulations.

    • Main Results:

    • Each prototype pattern is stored if and only if it is an asymptotically stable equilibrium point.
    • The basins of attraction for memory patterns are reasonably distributed in the Hamming distance sense.
    • The network exhibits high storage capacity, learning, and forgetting capabilities.
    • All network components are implementable.

    Conclusions:

    • The novel neural network provides a robust and efficient solution for associative memory.
    • The network's design ensures reliable pattern storage and retrieval.
    • The demonstrated performance suggests potential applications in AI and cognitive modeling.